CN109657943A - Dynamic assessment method, device and the electronic equipment of wind power plant operating states of the units - Google Patents
Dynamic assessment method, device and the electronic equipment of wind power plant operating states of the units Download PDFInfo
- Publication number
- CN109657943A CN109657943A CN201811483815.4A CN201811483815A CN109657943A CN 109657943 A CN109657943 A CN 109657943A CN 201811483815 A CN201811483815 A CN 201811483815A CN 109657943 A CN109657943 A CN 109657943A
- Authority
- CN
- China
- Prior art keywords
- principal component
- matrix
- data
- power plant
- wind power
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
Abstract
The present invention is applicable in wind power plant set state assessment technology field, dynamic assessment method, device and the electronic equipment of a kind of wind power plant operating states of the units is provided, this method comprises: being pre-processed to obtain data matrix to the operation data of wind power plant unit；The dynamic augmented matrix of the data matrix is constructed according to target time lag length；The covariance matrix of the dynamic augmented matrix is calculated by principal component analytical method；Principal component contributor rate is calculated according to the characteristic value of the covariance matrix and feature vector, and chooses principal component；The operating status of the wind power plant unit is judged by the principal component.Thus by the way that Principal Component Analysis to be applied in dynamic process, and according to the dynamic relationship between variable in the operation data of target time lag length analysis wind power plant unit, operating status that is more acurrate, efficiently assessing wind power plant unit in real time.
Description
Technical field
The invention belongs to the dynamic of wind power plant set state assessment technology field more particularly to wind power plant operating states of the units
State appraisal procedure, device and electronic equipment.
Background technique
With the development of economy and society, the energy contradiction of countries in the world becomes increasingly conspicuous.Wind energy have it is safe and clean, fill
Abundant, the features such as stabilization, wind energy utilizes the degree that effectively will alleviate resource supply and demand contradiction, slow down environmental pollution.In recent years,
Research of the China on wind-powered electricity generation and investment enter a new developing stage.But while wind power technology is grown rapidly, wind
The failure damage accident of electric field unit also increases year by year.Wind power plant unit is normally at remote and bad environments areas, unit
Maintenance work is difficult to carry out in time, increases the fund and human cost of wind power plant unit operation and maintenance.Therefore, how in wind
Incipient fault is detected in the operating status of electric field unit real-time, quickly and optimizes operating scheme to be current wind power plant unit emphasis
The direction of research.
Principal Component Analysis is a kind of Multielement statistical analysis method, using the thought of dimensionality reduction, if converting multiple indexs to
Dry overall target.Principal component analytical method is that high dimensional information is projected to lower-dimensional subspace, utmostly retains the original of data
Information, basic thought are: the new variables for finding one group of low-dimensional replaces the former variable of higher-dimension, and new variables is the line of former variable
Property combination.The change information that the former variable data of reaction that the new variables data of low-dimensional are more concentrated is included, according to data variation
Variance size determine the primary and secondary status of change direction, obtain principal component by primary and secondary sequence, successively referred to as first principal component,
Second principal component, etc. is independent from each other between these principal components.Dynamic Principal Component Analysis is by the structure of dynamic sequence data
Make a kind of new multicomponent statistics modeling method combined with Principal Component Analysis.The method will using Dynamic Time Series
The static data of former variable is extended to dynamic time data, by the analysis to dynamic time data, can simplify original number
According to the complexity of analysis, the dynamic relationship between system variable is efficiently extracted, improves and comments in the case where guaranteeing precision of prediction
Estimate efficiency.
The appraisal procedure of existing wind power plant operating states of the units is the method drawn using curve graph mostly, such as logical
Drafting power curve, part temperatures curve, pressure curve etc. are crossed to assess Wind turbines.The function of so-called Wind turbines
Rate curve generally refers to the relation curve that Wind turbines output power changes with wind speed.The actual efficiency of Wind turbines is mainly led to
The power curve for crossing Wind turbines actual motion reflected, the fine or not concentrated expression of actual power curve Wind turbines
Economy.However by single performance curve only can reflect wind power plant or single unit operation whether good, economy
Whether up to standard, for discovery potential risk, finding the first-class aspect of the source of trouble, there are many more insufficient.If all operation datas
Curve graph is drawn, Lai Yiyi compares observation, although overall operation state can be grasped, heavy workload, time and effort consuming,
It is not a kind of efficient appraisal procedure.
Summary of the invention
The purpose of the present invention is to provide the dynamic assessment method of wind power plant operating states of the units, device and electronic equipment,
It aims to solve the problem that since the prior art accurately and efficiently the operating status to wind power plant unit can not carry out real-time dynamic evaluation
Problem.
In a first aspect, the present invention provides a kind of dynamic assessment method of wind power plant operating states of the units, the method packet
Include following step:
The operation data of wind power plant unit is pre-processed to obtain data matrix；
The dynamic augmented matrix of the data matrix is constructed according to target time lag length；
The covariance matrix of the dynamic augmented matrix is calculated by principal component analytical method；
Principal component contributor rate is calculated according to the characteristic value of the covariance matrix and feature vector, and chooses principal component；
The operating status of the wind power plant unit is judged by the principal component.
Optionally, being pre-processed the step of obtaining data matrix to the operation data of wind power plant unit includes:
Data cleansing is carried out to the operation data of the wind power plant unit, modifies the wrong data in the operation data.
Data matrix will be configured to by the operation data of wrong data modification.
Optionally, will include: the step of data matrix is configured to by the operation data of wrong data modification
Data matrix is constructed to after the operation data that wrong data is modified is standardized；
Optionally, the step of dynamic augmented matrix of the data matrix is constructed according to time lag length include:
Calculate the time lag length of the operation data；
Time lag augmented matrix is constructed according to the time lag length；
The time lag augmented matrix is standardized to obtain dynamic augmented matrix.
Optionally, the step of calculating the time lag length of the operation data include:
Calculate the dynamic of Unequal time lag length when static relation number and time lag length without time lag length are continuously increased
Relationship number；
Target time lag length is determined according to the static relation number and the dynamic relationship number.
Optionally, principal component contributor rate is calculated according to the characteristic value of the covariance matrix and feature vector, and chooses master
The step of ingredient includes:
Calculate the characteristic value and feature vector of the covariance matrix；
Principal component scores and corresponding principal component coefficient are calculated by the characteristic value and feature vector；
Principal component contributor rate is calculated by the principal component scores and corresponding principal component coefficient, and chooses principal component.
Optionally, the step of judging the operating status of the wind power plant unit by the principal component include:
According to the principal component contributor rate drawing data figure of each principal component；
The operating status of the wind power plant unit is judged by the comparison of told datagraphic.
Second aspect provides a kind of dynamic evaluation device of wind power plant operating states of the units, comprising:
Preprocessing module is pre-processed to obtain data matrix for the operation data to wind power plant unit；
Dynamic augmented matrix computing module, for constructing the dynamic augmentation of the data matrix according to target time lag length
Matrix；
Covariance matrix computing module, for calculating the association side of the dynamic augmented matrix by principal component analytical method
Poor matrix；
Principal component contributor rate computing module is led for being calculated according to the characteristic value and feature vector of the covariance matrix
Components contribution rate, and choose principal component；
Operating status judgment module, for judging the operating status of the wind power plant unit by the principal component.
The third aspect provides a kind of electronic equipment, comprising:
Processor；And
The memory being connect with the processor communication；Wherein,
The memory is stored with readable instruction, and the readable instruction realizes such as the when being executed by the processor
Method described in one side.
Fourth aspect provides a kind of computer readable storage medium, is stored thereon with computer program, the meter
Calculation machine program realizes the method such as first aspect when executed.
The present invention is dynamic by the way that Principal Component Analysis to be applied to when the operating status to wind power plant unit is assessed
During state, and according to the dynamic relationship between variable in the operation data of target time lag length analysis wind power plant unit, thus more
The operating status of wind power plant unit is accurately and efficiently assessed in real time.
Detailed description of the invention
Fig. 1 is the implementation process of the dynamic assessment method for the wind power plant operating states of the units that the embodiment of the present invention one provides
Figure；
Fig. 2 is a kind of method flow diagram of calculating time lag length shown according to embodiment one；
Fig. 3 shows the block diagram of the dynamic evaluation device of wind power plant operating states of the units provided by Embodiment 2 of the present invention；
Fig. 4 be the embodiment of the present invention three provide to wind power plant operating states of the units carry out dynamic evaluation when principal component
Contribution rate schematic diagram；
Fig. 5 is variant work when carrying out dynamic evaluation to wind power plant operating states of the units that the embodiment of the present invention three provides
The principal component scores schematic diagram of condition；
Fig. 6 be the embodiment of the present invention three provide to wind power plant operating states of the units carry out dynamic evaluation when three kinds of operating conditions
The drafting schematic diagram of lower covariance matrix characteristic value；
Fig. 7 is the structural block diagram for the electronic equipment 100 that the embodiment of the present invention four provides.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to the accompanying drawings and embodiments,
The present invention will be described in further detail.It should be appreciated that specific embodiment described herein is only used to explain this hair
It is bright, it is not intended to limit the present invention.
Specific implementation of the invention is described in detail below in conjunction with specific embodiment:
Embodiment one:
Fig. 1 shows the realization of the dynamic assessment method of the wind power plant operating states of the units of the offer of the embodiment of the present invention one
Process, the dynamic assessment method for the wind power plant operating states of the units that embodiment one provides can run various with computer, server etc.
In electronic equipment, for ease of description, only parts related to embodiments of the present invention are shown, and details are as follows:
Step S110 is pre-processed to obtain data matrix to the operation data of wind power plant unit.
The embodiment of the present invention is suitable for the electronic equipments such as computer, server, and processor is arranged in these electronic equipments, with
Dynamic evaluation is carried out to the operating status of wind power plant unit.
Operation data is generated various data, such as temperature, power, pressure etc. in wind power plant unit running process
Data.
It is understood that the operation data of wind power plant unit be with time change, itself be it is spuious, because
This converts data matrix for spuious operation data by pre-processing to operation data, so to data matrix into
Row processing, can more convenient carry out Modeling analysis, the efficiency of the data processing effectively improved.
Data prediction, which refers to, handles operation data, retains most important data information, and constructs data square
Battle array.For example, data prediction may include data cleansing and data normalization:
(1) data cleansing
Due to being inevitably generated error in data acquisition, for the original operation number of wind power plant unit
According to needing to carry out data consistent check.According to the reasonable value range and correlation of each data, whether data are checked
It meets the requirements.If it was found that beyond normal range (NR), unreasonable or conflicting data in logic, need to carry out data modification
Or delete, and data are estimated using the sample average of certain item data, median, instead of missing data.For example, right
In partially due to the of short duration invalid data to rest or the interruption of Wind turbines instantaneity is obtained of detection device, needs to count
According to deletion, to keep the continuity of data.
(2) data normalization
For wind power plant operation data, all data index dimension is different, and the degree of scatter of data value is larger, is counting
When calculating covariance matrix, population variance can be controlled by the biggish data of some variance.Therefore, to further increase at data
The accuracy of reason, avoids the occurrence of error as far as possible, dimension impact is eliminated by being standardized to data, and then marking
Standardization processing building data matrix.For example, Z-score Standardization Act is to carry out data based on the mean value of data and standard deviation
Standardization.
Step S120 constructs the dynamic augmented matrix of data matrix according to target time lag length.
In actual condition, due to being influenced by inevitable disturbance factor, system running state can usually occur
Deviate, and the amplitude deviateed is typically small, remains within the scope of nominal situation.Therefore, by with dynamic pivot point
Analysis obtains the characteristic of deviation oscillation in real operating condition, i.e. correlation of the actual operating data in time series, finds out most phase
The range of the time series of pass, thus the disturbance factor of extraction process to the full extent.
Target time lag length is actual operating data relevant time range in time series.Target time lag length can
Be it is pre-set, be also possible to be calculated according to specific operation data.
The time lag length L that adaptability is calculated according to specific operation data, can find out maximally related time series
Range, so that the disturbance factor of extraction process to the full extent, farthest estimates the position that will be broken down.
When calculating target time lag length, the quiescent conditions that time lag length is zero are considered first, find out static relation number, it is quiet
State relationship number is equal to the difference of variable number and principal component number；
Then enable time lag length be 1, calculate dynamic relationship number, dynamic relationship number be equal to variable subtract principal component number and
(1) the static relation number in；
Time lag length is enabled to gradually increase again, according to recurrence formulaIt calculates new
Dynamic relationship number, work as rnew(l)≤0, i.e., not new static state and dynamic relationship, L is target time lag length at this time.
Specifically, Fig. 2 is a kind of method flow diagram of calculating time lag length shown according to embodiment one.
Step S130 calculates the covariance matrix of dynamic augmented matrix by principal component analytical method.
PCA (Principal Components Analysis) i.e. principal component analytical method, it is intended to utilize the think of of dimensionality reduction
Think, multi objective is converted into a few overall target.
In statistics, principal component analytical method PCA is a kind of technology of simplified data set.It is a linear transformation.
This transformation transforms the data into a new coordinate system, so that the first big variance of any data projection is at first
On coordinate (referred to as first principal component), the second largest variance on second coordinate (Second principal component), and so on.Principal component
Analysis method through the common dimension for reducing data set, while keep data set to the maximum feature of variance contribution.This is to pass through
Retain low order principal component, ignores what high-order principal component was accomplished.The low order ingredient most important side that tends to retain data in this way
Face.
Data matrix is extended according to the time lag length being calculated, the time lag augmentation square with L time lag length
Battle array may be expressed as:
Wherein X ∈ Rn+m, XT tRefer to the observed quantity tieed up in t moment m.
After time lag augmented matrix construction complete, dynamic data battle array X (l) is standardized using Z-score Standardization Act
Processing obtains dynamic augmented matrix.
Step S140 calculates principal component contributor rate according to the characteristic value of covariance matrix and feature vector, and choose it is main at
Point.
The analysis phase of data is unfolded based on Principal Component Analysis, during the analysis and assessment of operating status,
Principal component is extracted according to principal component contributor rate, and analyze and determine to principal component the operating status of wind power plant unit.
It optionally, can be to the simple segment processing of progress after obtaining dynamic augmented matrix.By observing emphasis number
According to variation or rendering parameter curve, to judge whether all data has apparent fluctuation, if data are within a certain range
Larger fluctuation has occurred, different from variation tendency before, this range data will carry out independent analysis as special operation condition,
To improve the specific aim of data processing, other operating conditions is avoided to impact the analysis of special operation condition, to further increase dynamic
The accuracy of state assessment.
Every kind of performance analysis method is similar, below by taking a kind of operating condition as an example, to illustrate the analytic process of the present embodiment.
(1) covariance matrix of dynamic Augmented Data matrix is found out.The association of dynamic augmented matrix is found out by PCA method
Variance matrix, the relationship between measure dimension and dimension, convenient for seeking matrix exgenvalue:
(2) seek covariance matrix characteristic value and corresponding unit character vector.By covariance matrix Eigenvalues Decomposition
Characteristic value diagonal matrix is obtained, further obtains eigenvectors matrix and by its orthogonalization.The feature of the covariance matrix of sample
Vector is able to reflect out sample distribution and converts most violent direction, and the size of characteristic value represents orthogonal basis to linear space
Weighing factor can be seen that variation tendency and the direction of data by the characteristic value and feature vector of covariance matrix:
X=U Λ0VT
Wherein ∧ ∈ RN×NIt is diagonal matrix, contains characteristic value Λ=[λ of covariance matrix1,λ2,…λN]；Covariance
Matrix can be decomposed as follows:
(3) related coefficients such as principal component scores, principal component coefficient are calculated.It can be by dynamic augmentation square by pivot analysis
Battle array is decomposed into load vectors piWith score vector tiThe sum of products add residual error E:
K in formula indicates the pivot number chosen, for representing the maximum principal component space of variance in data.Usual situation
Under, choosing each pivot number of k can include the 95% of data population variance.
(4) principal component contributor rate is found out, principal component is picked out according to principal component contributor rate.If selected principal component
Number is very little, can lose data information, and error is larger；When selected principal component is excessive, excessive useless letter can be included
Breath increases the complexity of analysis with diagnosis.Principal component contributor rate closer to be 1, then the principal component of description selection include it is original
Information is more.Contribution rate of accumulative total acquires according to the following formula:
Optionally, the preceding k ingredient that contribution rate of accumulative total is greater than 95% can be can be used as principal component.
Step S150 judges the operating status of wind power plant unit by principal component.
After choosing principal component, the operating status of wind power plant unit can be judged by calculating principal component scores.
For example, being calculated by the following formula principal component scores T=XP, then principal component scores are shown with scatter plot, will be assisted
Variance matrix feature value vector is depicted as Plato.It, can be with through the test pattern of output compared with nominal situation detects figure
Judge that the operating condition of Wind turbines breaks down.
Using method as described above, by the way that Principal Component Analysis is applied in dynamic process, and according to target time lag
Dynamic relationship in the operation data of length analysis wind power plant unit between variable, so that more acurrate, efficiently real-time assess wind-powered electricity generation
The operating status of field unit.
Embodiment two:
Fig. 3 shows the block diagram of the dynamic evaluation device of wind power plant operating states of the units provided by Embodiment 2 of the present invention,
For ease of description, only parts related to embodiments of the present invention are shown, including:
Preprocessing module 110 is pre-processed to obtain data matrix for the operation data to wind power plant unit；
Dynamic augmented matrix computing module 120, the dynamic for constructing the data matrix according to target time lag length increase
Wide matrix；
Covariance matrix computing module 130, for calculating the association of the dynamic augmented matrix by principal component analytical method
Variance matrix；
Principal component contributor rate computing module 140, for being calculated according to the characteristic value and feature vector of the covariance matrix
Principal component contributor rate, and choose principal component；
Operating status judgment module 150, for judging the operating status of the wind power plant unit by the principal component.
In embodiments of the present invention, each module of the dynamic evaluation device of the wind power plant operating states of the units can be by corresponding
Hardware or software unit realize that each module can be independent soft and hardware module, also can integrate as a soft and hardware list
Member, herein not to limit the present invention.The specific embodiment of each module can refer to the description of embodiment one, no longer superfluous herein
It states.
Embodiment three:
Embodiment three is the principal component analysis to the dynamic assessment method of wind power plant operating states of the units provided by the invention
Acetonideexample.
(1) selection of principal component
Principal component contributor rate is calculated, as shown in figure 4, the contribution rate of accumulative total of first five principal component has reached 85% or so,
Enough information is contained, so choosing number of principal components is five.
(2) analysis of principal component scores scatter plot and covariance matrix characteristic value bar chart
It is divided in the operating condition of analysis phase complete paired data, operating condition is divided into three kinds, it is main to the first of three kinds of operating conditions respectively
Ingredient, third principal component scores are drawn, as shown in Fig. 5 (a), 5 (b), 5 (c).From the graph, it is apparent that the first
Operating condition is similar with the principal component scores graphics shape of the third operating condition, and principal component scores value range is also roughly the same, and second
Kind operating condition principal component scores figure is significantly different, disperses and discontinuous so preliminary judgement, runs out in second of operating condition unit
Abnormal conditions are showed.
Fig. 6 (a), 6 (b), 6 (c) are the bar charts drawn according to covariance matrix characteristic value under three kinds of operating conditions, from the figure
As can be seen that the first principal component characteristic value under second of operating condition is apparently higher than the characteristic value under first and the third operating condition, from
And further confirmed that under second of operating condition, there is failure in the operation of wind power plant unit.
Example IV:
The structural block diagram that Fig. 7 shows the electronic equipment 100 of the offer of the embodiment of the present invention four is only shown for ease of description
Part related to the embodiment of the present invention is gone out.
With reference to Fig. 7, electronic equipment 100 may include one or more following component: processing component 101, memory
102, power supply module 103, multimedia component 104, audio component 105, sensor module 107 and communication component 108.Wherein,
Said modules and be not all it is necessary, electronic equipment 100 can according to itself functional requirement increase other assemblies or reduce it is certain
Component, this embodiment is not limited.
The integrated operation of the usual controlling electronic devices 100 of processing component 101, it is such as logical with display, call, data
Letter, camera operation and the associated operation of record operation etc..Processing component 101 may include one or more processors 109
It executes instruction, to complete all or part of the steps of aforesaid operations.In addition, processing component 101 may include one or more
Module, convenient for the interaction between processing component 101 and other assemblies.For example, processing component 101 may include multi-media module,
To facilitate the interaction between multimedia component 104 and processing component 101.
Memory 102 is configured as storing various types of data to support the operation in electronic equipment 100.These numbers
According to example include any application or method for being operated on electronic equipment 100 instruction.Memory 102 can be with
It is realized by any kind of volatibility or non-volatile memory device or their combination, such as SRAM (Static Random
Access Memory, static random access memory), EEPROM (Electrically Erasable Programmable
Read-Only Memory, electrically erasable programmable read-only memory), EPROM (Erasable Programmable Read
Only Memory, Erasable Programmable Read Only Memory EPROM), (Programmable Read-Only Memory, can compile PROM
Journey read-only memory), ROM (Read-Only Memory, read-only memory), magnetic memory, flash memory, disk or light
Disk.One or more modules are also stored in memory 102, which is configured to by the one or more
Processor 109 executes, to complete all or part of step in following any shown method.
Power supply module 103 provides electric power for the various assemblies of electronic equipment 100.Power supply module 103 may include power supply pipe
Reason system, one or more power supplys and other with for electronic equipment 100 generate, manage, and distribute the associated component of electric power.
Multimedia component 104 includes the screen of one output interface of offer between electronic equipment 100 and user.?
In some embodiments, screen may include LCD (Liquid Crystal Display, liquid crystal display) and TP (Touch
Panel, touch panel).If screen includes touch panel, screen may be implemented as touch screen, from the user to receive
Input signal.Touch panel includes one or more touch sensors to sense the gesture on touch, slide, and touch panel.
The touch sensor can not only sense the boundary of a touch or slide action, but also detect and grasp with the touch or sliding
Make relevant duration and pressure.
Audio component 105 is configured as output and/or input audio signal.For example, audio component 105 includes a wheat
Gram wind, when electronic equipment 100 is in operation mode, when such as call mode, recording mode, and voice recognition mode, microphone quilt
It is configured to receive external audio signal.The received audio signal can be further stored in memory 102 or via communication
Component 108 is sent.In some embodiments, audio component 105 further includes a loudspeaker, is used for output audio signal.
Sensor module 107 includes one or more sensors, for providing the shape of various aspects for electronic equipment 100
State assessment.For example, sensor module 107 can detecte the state that opens/closes of electronic equipment 100, component it is relatively fixed
Position, the coordinate that sensor module 107 can also detect 100 1 components of electronic equipment 100 or electronic equipment changes and electronics
The temperature change of equipment 100.In some embodiments, which can also include Magnetic Sensor, pressure sensing
Device or temperature sensor.
Communication component 108 is configured to facilitate the logical of wired or wireless way between electronic equipment 100 and other equipment
Letter.Electronic equipment 100 can access the wireless network based on communication standard, such as WiFi (Wireless-Fidelity, wireless network
Network), 2G or 3G or their combination.In one exemplary embodiment, communication component 108 comes from via broadcast channel reception
The broadcast singal or broadcast related information of external broadcasting management system.In one exemplary embodiment, the communication component
108 further include NFC (Near Field Communication, near-field communication) module, to promote short range communication.For example, in NFC
Module can be based on RFID (Radio Frequency Identification, radio frequency identification) technology, IrDA (Infrared
Data Association, Infrared Data Association) technology, UWB (Ultra-Wideband, ultra wide band) technology, BT
(Bluetooth, bluetooth) technology and other technologies are realized.
In the exemplary embodiment, electronic equipment 100 can be by one or more ASIC (Application Specific
Integrated Circuit, application specific integrated circuit), DSP (Digital Signal Processing, digital signal
Processor), PLD (Programmable Logic Device, programmable logic device), FPGA (Field-
Programmable Gate Array, field programmable gate array), controller, microcontroller, microprocessor or other electronics
Element is realized, for executing the above method.
The concrete mode that processor executes operation in electronic equipment in the embodiment is transported in the related wind power plant unit
It is described in detail in the embodiment of the dynamic assessment method of row state, will no longer elaborate explanation herein.It is described above
Only presently preferred embodiments of the present invention is not intended to limit the invention, and is made all within the spirits and principles of the present invention
Any modifications, equivalent replacements, and improvements etc., should all be included in the protection scope of the present invention.
Optionally, the present invention also provides a kind of equipment, execute it is any of the above-described shown in the intelligence of packing case switch state know
The all or part of step of other method.The equipment includes:
At least one processor；And
The memory being connect at least one described processor communication；Wherein,
The memory be stored with can by least one described processor execute instruction, described instruction by it is described at least
One processor executes, so that at least one described processor is able to carry out the side as described in any of the above-described exemplary embodiments
Method.
Processor executes the concrete mode of operation in the related packing case switch state in equipment in the embodiment
Intelligent identification Method embodiment in perform detailed description, no detailed explanation will be given here.
In the exemplary embodiment, a kind of storage medium is additionally provided, which is computer-readable storage medium
Matter, such as can be the provisional and non-transitorycomputer readable storage medium for including instruction.The storage medium for example including
The memory 102 of instruction, above-metioned instruction can be executed by the processor 109 of equipment 100 to complete above-mentioned packing case switch state
Intelligent identification Method.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all in essence of the invention
Made any modifications, equivalent replacements, and improvements etc., should all be included in the protection scope of the present invention within mind and principle.
Claims (10)
1. a kind of dynamic assessment method of wind power plant operating states of the units, which is characterized in that the method includes the following steps:
The operation data of wind power plant unit is pre-processed to obtain data matrix；
The dynamic augmented matrix of the data matrix is constructed according to target time lag length；
The covariance matrix of the dynamic augmented matrix is calculated by principal component analytical method；
Principal component contributor rate is calculated according to the characteristic value of the covariance matrix and feature vector, and chooses principal component；
The operating status of the wind power plant unit is judged by the principal component.
2. the method as described in claim 1, which is characterized in that pre-processed and counted to the operation data of wind power plant unit
Include: according to the step of matrix
Data cleansing is carried out to the operation data of the wind power plant unit, modifies the wrong data in the operation data；
Data matrix will be configured to by the operation data of wrong data modification.
3. method according to claim 2, which is characterized in that will be configured to by the operation data of wrong data modification
The step of data matrix includes:
Data matrix is constructed to after the operation data that wrong data is modified is standardized.
4. the method as described in claim 1, which is characterized in that construct the dynamic augmentation of the data matrix according to time lag length
The step of matrix includes:
Calculate the time lag length of the operation data；
Time lag augmented matrix is constructed according to the time lag length；
The time lag augmented matrix is standardized to obtain dynamic augmented matrix.
5. method as claimed in claim 4, which is characterized in that the step of calculating the time lag length of the operation data include:
Calculate the dynamic relationship of Unequal time lag length when static relation number and time lag length without time lag length are continuously increased
Number；
Target time lag length is determined according to the static relation number and the dynamic relationship number.
6. the method as described in claim 1, which is characterized in that according to the characteristic value of the covariance matrix and feature vector meter
Principal component contributor rate is calculated, and the step of choosing principal component includes:
Calculate the characteristic value and feature vector of the covariance matrix；
Principal component scores and corresponding principal component coefficient are calculated by the characteristic value and feature vector；
Principal component contributor rate is calculated by the principal component scores and corresponding principal component coefficient, and chooses principal component.
7. the method as described in claim 1, which is characterized in that judge the operation of the wind power plant unit by the principal component
The step of state includes:
According to the principal component contributor rate drawing data figure of each principal component；
The operating status of the wind power plant unit is judged by the comparison of told datagraphic.
8. a kind of dynamic evaluation device of wind power plant operating states of the units, which is characterized in that described device includes:
Preprocessing module is pre-processed to obtain data matrix for the operation data to wind power plant unit；
Dynamic augmented matrix computing module, for constructing the dynamic augmented matrix of the data matrix according to target time lag length；
Covariance matrix computing module, for calculating the covariance square of the dynamic augmented matrix by principal component analytical method
Battle array；
Principal component contributor rate computing module, for calculating principal component tribute according to the characteristic value and feature vector of the covariance matrix
Rate is offered, and chooses principal component；
Operating status judgment module, for judging the operating status of the wind power plant unit by the principal component.
9. a kind of electronic equipment, which is characterized in that the electronic equipment includes:
Processor；And
The memory being connect with the processor communication；Wherein,
The memory is stored with readable instruction, and the readable instruction realizes such as claim when being executed by the processor
The described in any item methods of 1-7.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer journey
Sequence realizes the method according to claim 1 to 7 when executed.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811483815.4A CN109657943A (en) | 2018-12-06 | 2018-12-06 | Dynamic assessment method, device and the electronic equipment of wind power plant operating states of the units |
| PCT/CN2019/123254 WO2020114449A1 (en) | 2018-12-06 | 2019-12-05 | Method and apparatus for dynamically assessing operation state of wind power station unit, and electronic device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811483815.4A CN109657943A (en) | 2018-12-06 | 2018-12-06 | Dynamic assessment method, device and the electronic equipment of wind power plant operating states of the units |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109657943A true CN109657943A (en) | 2019-04-19 |
Family
ID=66112556
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811483815.4A Pending CN109657943A (en) | 2018-12-06 | 2018-12-06 | Dynamic assessment method, device and the electronic equipment of wind power plant operating states of the units |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN109657943A (en) |
| WO (1) | WO2020114449A1 (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020114449A1 (en) * | 2018-12-06 | 2020-06-11 | 中国科学院深圳先进技术研究院 | Method and apparatus for dynamically assessing operation state of wind power station unit, and electronic device |
| CN112906177A (en) * | 2019-12-04 | 2021-06-04 | 财团法人资讯工业策进会 | Apparatus and method for generating a motor diagnostic model |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106444666A (en) * | 2016-09-22 | 2017-02-22 | 宁波大学 | Dynamic process monitoring method based on weighted dynamic distributed PCA model |
| CN108196165A (en) * | 2018-01-09 | 2018-06-22 | 贵州大学 | Power grid abnormal state detection method based on sample covariance matrix maximum eigenvalue |
| CN108572639A (en) * | 2018-03-19 | 2018-09-25 | 宁波大学 | A kind of dynamic process monitoring method rejected based on principal component autocorrelation |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8924162B2 (en) * | 2010-05-13 | 2014-12-30 | University Of Cincinnati | Turbine-to-turbine prognostics technique for wind farms |
| CN105303468A (en) * | 2015-11-20 | 2016-02-03 | 国网天津市电力公司 | Comprehensive evaluation method of smart power grid construction based on principal component cluster analysis |
| CN105677791B (en) * | 2015-12-31 | 2019-03-08 | 新疆金风科技股份有限公司 | For analyzing the method and system of the operation data of wind power generating set |
| CN109657943A (en) * | 2018-12-06 | 2019-04-19 | 中国科学院深圳先进技术研究院 | Dynamic assessment method, device and the electronic equipment of wind power plant operating states of the units |
-
2018
- 2018-12-06 CN CN201811483815.4A patent/CN109657943A/en active Pending
-
2019
- 2019-12-05 WO PCT/CN2019/123254 patent/WO2020114449A1/en active Application Filing
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106444666A (en) * | 2016-09-22 | 2017-02-22 | 宁波大学 | Dynamic process monitoring method based on weighted dynamic distributed PCA model |
| CN108196165A (en) * | 2018-01-09 | 2018-06-22 | 贵州大学 | Power grid abnormal state detection method based on sample covariance matrix maximum eigenvalue |
| CN108572639A (en) * | 2018-03-19 | 2018-09-25 | 宁波大学 | A kind of dynamic process monitoring method rejected based on principal component autocorrelation |
Non-Patent Citations (1)
| Title |
|---|
| 龚婷婷: "基于主元分析方法的炼油厂蒸馏过程故障诊断研究", 《中国硕士学位论文全文数据库（电子期刊）信息科技辑》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020114449A1 (en) * | 2018-12-06 | 2020-06-11 | 中国科学院深圳先进技术研究院 | Method and apparatus for dynamically assessing operation state of wind power station unit, and electronic device |
| CN112906177A (en) * | 2019-12-04 | 2021-06-04 | 财团法人资讯工业策进会 | Apparatus and method for generating a motor diagnostic model |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2020114449A1 (en) | 2020-06-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11624731B2 (en) | Method for predicting remaining life of numerical control machine tool | |
| CN104595170B (en) | A kind of air compressor machine monitoring and diagnosis system and method for self-adaptive kernel gauss hybrid models | |
| CN100470417C (en) | Fault diagnostic system and method for under industrial producing process small sample condition | |
| Zheng et al. | Electricity theft detecting based on density-clustering method | |
| CN102339389A (en) | Fault detection method for one-class support vector machine based on density parameter optimization | |
| CN114676742A (en) | Power grid abnormal electricity utilization detection method based on attention mechanism and residual error network | |
| CN111898669A (en) | Machine learning-based direct-current submerged arc furnace abnormal event early warning system | |
| CN110032799A (en) | A kind of the angle similarity divided stages and monitoring method of microbiological pharmacy process | |
| CN116824517B (en) | Substation operation and maintenance safety control system based on visualization | |
| CN109657943A (en) | Dynamic assessment method, device and the electronic equipment of wind power plant operating states of the units | |
| CN110766320A (en) | Method and device for evaluating operation safety of airport intelligent power grid | |
| CN111273125A (en) | RST-CNN-based power cable channel fault diagnosis method | |
| CN115442212A (en) | Intelligent monitoring analysis method and system based on cloud computing | |
| Hu et al. | Building occupancy detection and localization using cctv camera and deep learning | |
| Zu et al. | A simple gated recurrent network for detection of power quality disturbances | |
| CN117713221B (en) | Micro-inversion photovoltaic grid-connected optimization system | |
| CN117368862A (en) | High-efficiency weather radar data quality evaluation system | |
| CN114997342B (en) | SCR fault diagnosis method, device, equipment and storage medium | |
| CN116909712A (en) | Intelligent task scheduling system and method based on machine learning | |
| CN116704729A (en) | Industrial kiln early warning system and method based on big data analysis | |
| Yu et al. | A hybrid learning-based model for on-line monitoring and diagnosis of out-of-control signals in multivariate manufacturing processes | |
| CN114021465A (en) | Electric power system robust state estimation method and system based on deep learning | |
| CN110647922B (en) | Layered non-Gaussian process monitoring method based on public and special feature extraction | |
| Yang et al. | Prediction of criminal tendency of high-risk personnel based on combination of principal component analysis and support vector machine | |
| Gao et al. | The design of the prognostics and health management system for special vehicle |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190419 |
|
| RJ01 | Rejection of invention patent application after publication |