CN107147143B - Method for establishing early warning model of fan interlocking off-line fault - Google Patents
Method for establishing early warning model of fan interlocking off-line fault Download PDFInfo
- Publication number
- CN107147143B CN107147143B CN201710379893.9A CN201710379893A CN107147143B CN 107147143 B CN107147143 B CN 107147143B CN 201710379893 A CN201710379893 A CN 201710379893A CN 107147143 B CN107147143 B CN 107147143B
- Authority
- CN
- China
- Prior art keywords
- early warning
- window
- variance
- data
- autocorrelation coefficient
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 31
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 33
- 230000035772 mutation Effects 0.000 claims abstract description 4
- 238000005070 sampling Methods 0.000 claims description 39
- 238000004364 calculation method Methods 0.000 claims description 35
- 230000008569 process Effects 0.000 claims description 7
- 230000000630 rising effect Effects 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- YTAHJIFKAKIKAV-XNMGPUDCSA-N [(1R)-3-morpholin-4-yl-1-phenylpropyl] N-[(3S)-2-oxo-5-phenyl-1,3-dihydro-1,4-benzodiazepin-3-yl]carbamate Chemical compound O=C1[C@H](N=C(C2=C(N1)C=CC=C2)C1=CC=CC=C1)NC(O[C@H](CCN1CCOCC1)C1=CC=CC=C1)=O YTAHJIFKAKIKAV-XNMGPUDCSA-N 0.000 claims description 2
- 238000005065 mining Methods 0.000 claims description 2
- 238000004458 analytical method Methods 0.000 description 4
- 230000007246 mechanism Effects 0.000 description 4
- 230000007704 transition Effects 0.000 description 3
- 230000003111 delayed effect Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 108010076504 Protein Sorting Signals Proteins 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000005094 computer simulation Methods 0.000 description 1
- 230000007123 defense Effects 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000010355 oscillation Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 238000004904 shortening Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
- 230000001131 transforming effect Effects 0.000 description 1
Classifications
-
- H02J3/386—
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
- H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E10/00—Energy generation through renewable energy sources
- Y02E10/70—Wind energy
- Y02E10/76—Power conversion electric or electronic aspects
Landscapes
- Testing And Monitoring For Control Systems (AREA)
- Control Of Positive-Displacement Air Blowers (AREA)
Abstract
The invention discloses a method for establishing a fan interlocking off-grid fault early warning model, which utilizes voltage data of a wind power plant grid-connected point monitored by a wind power plant SCADA system in real time, and utilizes wavelet decomposition to extract a high-frequency dynamic signal of the data before voltage drop based on the critical moderation early warning principle; and then, selecting a proper sliding window for the signal to calculate the variance and the autocorrelation coefficient so as to find the early warning signal of the system before voltage mutation, and analyzing the stability of the early warning signal by calculating the variance and the autocorrelation coefficient of the high-frequency signal of wavelet decomposition of different orders under different window lengths. Under the condition that an accurate network model is not established, the statistical characteristics of critical slowing in voltage time sequence data are identified, and early warning is given out before voltage drops, so that an early warning model of fan interlocking offline faults is obtained, and early warning of fan interlocking offline is realized.
Description
Technical Field
The invention relates to the technical field of power system security defense, in particular to a method for establishing a fan chain off-line fault early warning model based on a critical slowing theory.
Background
With the development of wind power technology, the scale of the wind power technology is larger, and the operation mechanism is more and more complex. Although the occurrence probability of the fan cascading failure is small, the caused consequences are serious, fault symptoms are discovered and early warning is given out in the early stage of the failure, and therefore the method has very important significance in monitoring and isolating areas or elements which are most likely to have secondary failures after the initial failure occurs.
The existing method for early warning of cascading failures is based on a cascading failure mechanism, a model is built to simulate a cascading failure occurrence process, so that the development trend of accidents and the resulting risk are estimated, and in the past more than ten years, domestic and foreign scholars do much research work in this respect, and some methods are provided, including: pattern search methods, model analysis methods, and the like. The concept of correcting betweenness in a complex network by using electrical parameters is adopted in a document 'cascading failure modeling and prevention research based on a complex network theory' and a document 'power grid cascading failure prediction under a small world network', a complex network model capable of simulating changes of physical quantities such as power flow and voltage is provided, and cascading failure propagation behaviors are predicted. No matter a mode search method or a model analysis method, a cascading failure model is established based on a failure mechanism so as to find out a propagation mode of cascading failures in the evolution process of a blackout accident, but the fan cascading off-line early warning models are limited by the accuracy of establishment of the cascading failure evolution model, a large number of topological parameters and system operation parameters are needed, and the time of taking emergency measures is delayed by the methods of off-line calculation and on-line detection, so that the expected control effect cannot be realized in the aspects of calculation accuracy and calculation duration.
In recent years, a method for predicting a blackout accident from operation state data provides a new idea for early warning of fan interlocking grid-disconnected faults, voltage and frequency changes can be obtained in the accident occurrence process through analysis of fan interlocking grid-disconnected accident mechanisms, the first batch of off-grid fans of a wind power plant are low in voltage, so that voltage time series data are analyzed, sign information before faults is excavated, early warning can be given before voltage drops, and a fan interlocking grid-disconnected early warning model is established.
Disclosure of Invention
The invention provides a fan interlocking off-line fault early warning model establishing method, which solves the problems that a large number of topological parameters and operation condition data are needed in the fan interlocking off-line fault early warning model establishing method in the prior art, the system modeling is difficult to establish and the like, provides reliable warning information for power operators, and provides solid technical support for preventing further worsening of accidents and effectively preventing interlocking off-line accidents.
The technical scheme adopted by the invention for solving the technical problems is as follows: a method for establishing an early warning model of fan interlocking off-line faults comprises the following steps:
s1: acquiring voltage data of a wind power plant grid-connected point monitored by a wind power plant SCADA system in real time, and taking the voltage data as observed quantity of a fan interlocking off-grid early warning model;
s2: collecting data before a fault from the observed quantity collected in the step S1, performing trend removing processing on the data before voltage drop by using wavelet decomposition based on the principle of critical moderation early warning, and extracting a high-frequency dynamic signal of the processed data;
s3: selecting a proper sliding window for calculating the variance and the autocorrelation coefficient of the high-frequency dynamic signal obtained in the step S2 to find an early warning signal of the system before voltage mutation;
s4: the stability of the early warning signal is analyzed by calculating the variance and autocorrelation coefficient of the high-frequency signal of wavelet decomposition with different orders under different window lengths.
In step S3, the calculation process of the variance value and the autocorrelation coefficient includes:
s301: setting a sliding window and a fixed hysteresis step length, and sliding the sliding window by adopting the step length;
s302: by the formulaCalculating the variance value in each window, wherein n represents the number of all sample points in each sampling window, and xiFor the sample data within the sampling window,the average value of the sample data in the sampling window is obtained;
s303: drawing a variance curve for the variance value in each window calculated in the S302, and mining early warning information of fan chain off-line according to the rising trend of the variance curve;
s304: selecting sample data by adopting a window with a fixed length;
s305: selecting variable with lag step j in window, marking the autocorrelation coefficient of variable j as R (j), and using formula to obtain the resultCalculating autocorrelation coefficients, wherein n represents the number of all sample points in each sampling window, x is the sample data in the sampling window,is the average value of the sample data in the sampling window, and s is the data x of the n sample pointsiThe variance of (a); judging the correlation between the time series value before the variable j and the time series value after the variable j through the autocorrelation coefficient;
s306: the autocorrelation coefficient r (j) value calculated in step S305 is plotted in a graph, and the critical transformation of the system is determined according to the rising trend of the autocorrelation coefficient.
Wherein the window length and the hysteresis step length selected in the variance calculation are different from the window length and the hysteresis step length selected in the autocorrelation coefficient calculation.
Wherein the step S4 includes the steps of:
s401: respectively selecting wavelets with different orders to decompose high-frequency signals;
s402: calculating variance and autocorrelation coefficients of the high-frequency signals of the wavelet decomposition with different orders obtained in the step S401 by adopting different window lengths respectively;
s403: and drawing a variance curve and an autocorrelation curve according to the calculation result, and judging the stability of early warning of the fan interlocking off-line fault through the rising trend of the curve.
In step S402, the calculation formulas of the variance S and the autocorrelation coefficient r (j) are respectively:where n denotes the number of sample points in each sampling window, xiFor the sample data within the sampling window,the average value of the sample data in the sampling window is obtained;where n represents the number of all sample points in each sampling window, x is the sample data within the sampling window,is the average value of the sample data in the sampling window, and s is the data x of the n sample pointsiThe variance of (c).
Compared with the prior art, the invention has the following beneficial effects: the method for establishing the early warning model of the fan interlocking off-line fault utilizes the high-resolution and time-synchronous measurement information obtained by a large number of measurement units in the system to intensively monitor the low-voltage signal causing the first fan off-line of the wind power plant after the inevitable initial fault, identifies the statistical characteristic of critical slowing in the voltage time sequence data under the condition of not establishing an accurate network model, and sends out the warning before the voltage drops, thereby obtaining the early warning model of the fan interlocking off-line fault, without a large number of topological parameters and system operation parameters, and avoiding the problem of time lag of taking emergency measures brought by the methods of off-line calculation and on-line detection, achieving the expected control effect in the aspects of calculation precision and calculation duration, shortening the calculation duration, and easily obtaining the measured value, has high practical value.
The invention is further explained in detail with the accompanying drawings and the embodiments; however, the method for establishing the early warning model of the fan interlocking off-line fault is not limited to the embodiment.
Drawings
FIG. 1 is a block flow diagram of the present invention;
FIG. 2 is a grid-connected point bus voltage curve diagram of a certain wind power plant feeder three-phase short circuit fault monitored by the wind power plant SCADA system;
FIG. 3 is a low frequency signal of the voltage sequence after 6 th order wavelet decomposition of the present invention;
FIG. 4 is a voltage sequence high frequency signal extracted by the 6 th order wavelet decomposition transform of the present invention;
FIG. 5 is a graph of variance of a high frequency signal of a voltage sequence extracted by a 6 th order wavelet decomposition transform according to the present invention;
FIG. 6 is a graph of the autocorrelation of the voltage sequence high frequency signal extracted by the 6 th order wavelet decomposition transform of the present invention;
FIG. 7 is a graph of variance of a high frequency signal after 7 th order wavelet decomposition in accordance with the present invention;
FIG. 8 is a graph of autocorrelation coefficients of a high frequency signal after 7 th order wavelet decomposition in accordance with the present invention;
FIG. 9 is a graph of variance of a high frequency signal after 5 th order wavelet decomposition in accordance with the present invention;
FIG. 10 is a graph of autocorrelation coefficients of a high frequency signal after 5 th order wavelet decomposition in accordance with the present invention;
FIG. 11 is a graph of autocorrelation coefficients of a high-frequency signal after 6 th order wavelet decomposition of the present invention at 1/3 with a window length being a calculation sequence;
FIG. 12 is a graph of autocorrelation coefficients of a high-frequency signal after 6 th order wavelet decomposition of the present invention at 1/2 with a window length being a calculation sequence;
FIG. 13 is a graph showing the variance of a high frequency signal after a 6 th order wavelet decomposition of the present invention at a window length of 20;
fig. 14 is a graph showing the variance of the high frequency signal after the 6 th order wavelet decomposition of the present invention at a window length of 50.
Detailed Description
In an embodiment, fig. 1 is a flow chart of a method for establishing an early warning model of a fan cascading offline fault, referring to fig. 1, the method includes the following steps:
s1: acquiring voltage data of a wind power plant grid-connected point monitored by a wind power plant SCADA system in real time, specifically acquiring grid-connected point bus voltage of a feeder three-phase short circuit fault of a certain wind power plant, and taking the grid-connected point bus voltage as observed quantity of a fan interlocking off-line early warning model as shown in FIG. 2;
s2: collecting data before a fault from the observed quantity collected in the step S1, performing trend removing processing on the data before voltage drop by using wavelet decomposition based on the principle of critical moderation early warning, and extracting a high-frequency dynamic signal of the processed data;
s3: selecting a proper sliding window for calculating the variance and the autocorrelation coefficient of the high-frequency dynamic signal obtained in the step S2 to find an early warning signal of the system before voltage mutation;
s4: the stability of the early warning signal is analyzed by calculating the variance and autocorrelation coefficient of the high-frequency signal of wavelet decomposition with different orders under different window lengths.
Referring to fig. 3 and 4, the wavelet decomposition is used for the observed quantity obtained in step S1 to obtain the high-frequency signal of the system, and the specific principle is as follows: wavelet decomposition inherits the thought of short-time Fourier transform, better time domain localization characteristics can be obtained by transforming the size of a window, the size of the window is changed along with frequency, a large window is adopted for low-frequency signals so as to avoid losing low-frequency information, and a small window is adopted for high-frequency signals so as to capture high-frequency dynamic information. In this embodiment, the voltage signal observed quantity obtained in step S1 is decomposed by using the most commonly used Daubechies wavelet, so that a voltage high-frequency signal can be obtained. Fig. 3 is a low-frequency part of a voltage signal sequence after 6-order wavelet decomposition, fig. 4 is a high-frequency signal extracted by 6-order wavelet transformation, and the high-frequency signal extracted in fig. 4 is used as an observation signal for fan chain off-line early warning.
Referring to fig. 5, corresponding to the calculation result of the variance of the high frequency signal in step S3, specifically, the variance calculation is performed on the time series of the voltage, first, the size of the sliding window is set to 50, the hysteresis step is set to 52, that is, the 1 st to 50 th samples are selected as the first sampling window, and the 51 st to 100 th samples are selected as the second sampling window, so that 1000 sample points can be divided into 20 sampling windows, and the formula is used for the samples in each sampling windowCalculating variance, wherein n is 50, xiFor the sample data within each sampling window,and calculating the average value of the sample data in each sampling window to obtain the variance curve of the voltage signals in 20 sampling windows. In fig. 5, when the fault occurs at the time of 9s, the variance signal starts to show signs of rising (abrupt increase points in the graph) before 8s, because the variance is obtained in a sampling window, and the signs of variance increase appear in the sampling window (7-8) s, so that the variance can be used as an early warning feature of critical slowdown. And before 7sIn the sample window, the variance is close to 0 because the voltage data obtained by simulation is relatively flat, the voltage fluctuation is also between 1.07p.u. and 1.65p.u., and the variance of the signal is approximately 0 under such small amplitude fluctuation. It can be further determined that the system high frequency fluctuation signal has an increasing variance as it approaches the critical transition point, which also means that the high frequency fluctuation begins to gradually deviate from the equilibrium state, forcing the system toward the critical point.
Referring to fig. 6, the window and the hysteresis step in the autocorrelation coefficient calculation process are different from the window and the hysteresis step in the variance corresponding to the calculation result of the autocorrelation coefficient of the high frequency signal in step S3. In the autocorrelation coefficient calculation process, the selection of the window length generally selects one half or one third of the calculation sequence, in this embodiment, one half of the calculation sequence is selected as the window length, the hysteresis step is 1, and the window length is calculated by the formulaCalculating the autocorrelation coefficient, wherein n represents the number of all sample points in each sampling window, and 50 is taken here, x is the sample data in the sampling window,is the average value of the sample data in the sampling window, and s is the data x of the n sample pointsiThe variance of (c). In fig. 6, the sign of the increase of the oscillation amplitude of the autocorrelation coefficient appears in the sampling window (7-8) s, and the increase of the autocorrelation coefficient indicates that the high-frequency signal has the characteristic of short-term memory before the system enters the critical transition state, that is, the data in the next sampling window and the data in the previous sampling window start to be similar, so that the increase of the autocorrelation coefficient provides an early warning signal for the system to enter the critical transition.
Referring to fig. 7-10, the calculation results of the high frequency signal variance and autocorrelation coefficient for wavelet decomposition of different orders in step S4 are corresponded; specifically, the calculation results of the 5 th order wavelet decomposition signal and the 7 th order wavelet decomposition signal are selected for comparison, the increase trend of the variance and the autocorrelation coefficient before voltage drop in the graph is unchanged, the difference is that the 7 th order wavelet decomposition result affects the calculation results of the variance and the autocorrelation coefficient, the increase trend is not clear in the 6 th order wavelet decomposition result, the 5 th order wavelet in fig. 9 and 10 affects the calculation results of the variance and the autocorrelation coefficient, the obtained early warning signal occurs in an 8 s-9 s interval and is more delayed than the early warning signal obtained by the 6 th order wavelet decomposition result, and therefore the order of the obtained wavelet decomposition can affect the accuracy of the result to a certain extent.
Referring to fig. 11-14, corresponding to the calculation results of the high frequency signal variance and autocorrelation coefficient at different window lengths in step S4; specifically, the 6 th order wavelet decomposition result is calculated by adopting different window lengths. For the variance, the window lengths are respectively selected to be 50 and 20, for the autocorrelation coefficients, the window lengths are respectively selected to be 1/2 and 1/3 of the calculation sequences, as shown in fig. 11 and 12, for the autocorrelation curves under different windows, the increasing trend near the critical point is constant, but the calculation sequences with longer window lengths can more clearly express the increasing trend of the autocorrelation coefficients of the system, the longer window lengths can contain more high-frequency dynamic information, and the autocorrelation analysis of the system is not easily affected by stray signals; as shown in fig. 13 and 14, the variance of the calculation sequence with a longer window is more obvious in increasing trend, while the calculation sequence with a shorter window is not significant in increasing trend of the variance of the high frequency signal because the detail signal in the signal is emphasized too much, so that it is more desirable to select a window with a longer length when calculating the variance of the high frequency signal.
The above embodiment is only used to further illustrate the method for establishing the early warning model of the fan interlocking grid-disconnection fault of the present invention, but the present invention is not limited to the embodiment, and any simple modification, equivalent change and modification made to the above embodiment according to the technical essence of the present invention fall within the protection scope of the technical solution of the present invention.
Claims (4)
1. A method for establishing an early warning model of a fan interlocking off-line fault is characterized by comprising the following steps:
s1: acquiring voltage data of a wind power plant grid-connected point monitored by a wind power plant SCADA system in real time, and taking the voltage data as observed quantity of a fan interlocking off-grid early warning model;
s2: collecting data before a fault from the observed quantity collected in the step S1, performing trend removing processing on the data before voltage drop by using wavelet decomposition based on the principle of critical moderation early warning, and extracting a high-frequency dynamic signal of the processed data;
s3: selecting a proper sliding window for calculating the variance and the autocorrelation coefficient of the high-frequency dynamic signal obtained in the step S2 to find an early warning signal of the system before voltage mutation;
s4: analyzing the stability of the early warning signal by calculating the variance and autocorrelation coefficient of the high-frequency signal of wavelet decomposition with different orders under different window lengths;
the calculation process of the variance value and the autocorrelation coefficient in step S3 is as follows:
s301: setting a sliding window and a fixed hysteresis step length, and sliding the sliding window by adopting the step length;
s302: by the formulaCalculating the variance value in each window, wherein n represents the number of all sample points in each sampling window, and xiFor the sample data within the sampling window,the average value of the sample data in the sampling window is obtained;
s303: drawing a variance curve for the variance value in each window calculated in the S302, and mining early warning information of fan chain off-line according to the rising trend of the variance curve;
s304: selecting sample data by adopting a window with a fixed length;
s305: selecting variable with lag step j in window, marking the autocorrelation coefficient of variable j as R (j), and using formula to obtain the resultCalculating the autocorrelation coefficient, wherein n represents the number of all sample points in each sampling window, and xi、xi+jFor the sample data within the sampling window,is the average value of the sample data in the sampling window, and s is the data x of the n sample pointsiThe variance of (a); judging the correlation between the time series value before the variable j and the time series value after the variable j through the autocorrelation coefficient;
s306: the autocorrelation coefficient r (j) value calculated in step S305 is plotted in a graph, and the critical transformation of the system is determined according to the rising trend of the autocorrelation coefficient.
2. The method for establishing the early warning model of the fan chain off-line fault according to claim 1, characterized by comprising the following steps of: the window length and the hysteresis step length selected in the variance calculation are different from the window length and the hysteresis step length selected in the autocorrelation coefficient calculation.
3. The method for establishing the early warning model of the fan chain off-line fault according to claim 1, characterized by comprising the following steps of: the step S4 includes the steps of:
s401: respectively selecting wavelets with different orders to decompose high-frequency signals;
s402: calculating variance and autocorrelation coefficients of the high-frequency signals of the wavelet decomposition with different orders obtained in the step S401 by adopting different window lengths respectively;
s403: and drawing a variance curve and an autocorrelation curve according to the calculation result, and judging the stability of early warning of the fan interlocking off-line fault through the rising trend of the curve.
4. The method for establishing the early warning model of the fan chain off-line fault according to claim 3, characterized by comprising the following steps of: in the step S402, the calculation formulas of the variance S and the autocorrelation coefficient r (j) are respectively:where n denotes the number of sample points in each sampling window, xiFor the sample data within the sampling window,the average value of the sample data in the sampling window is obtained;where n denotes the number of all sample points in each sampling window, xi、xi+jFor the sample data within the sampling window,is the average value of the sample data in the sampling window, and s is the data x of the n sample pointsiThe variance of (c).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710379893.9A CN107147143B (en) | 2017-05-25 | 2017-05-25 | Method for establishing early warning model of fan interlocking off-line fault |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710379893.9A CN107147143B (en) | 2017-05-25 | 2017-05-25 | Method for establishing early warning model of fan interlocking off-line fault |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107147143A CN107147143A (en) | 2017-09-08 |
| CN107147143B true CN107147143B (en) | 2019-12-31 |
Family
ID=59780197
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710379893.9A Active CN107147143B (en) | 2017-05-25 | 2017-05-25 | Method for establishing early warning model of fan interlocking off-line fault |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107147143B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110374907A (en) * | 2019-07-15 | 2019-10-25 | 山东浪潮人工智能研究院有限公司 | A kind of coal mine blower time series data method of sampling and tool based on concept drift |
| CN113534689B (en) * | 2020-04-13 | 2023-04-07 | 北京四维图新科技股份有限公司 | Delayed start control method and device |
| CN117150269B (en) * | 2023-09-04 | 2024-06-07 | 淮阴师范学院 | Electrical equipment operation abnormality diagnosis system based on data analysis |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102778358A (en) * | 2012-06-04 | 2012-11-14 | 上海东锐风电技术有限公司 | Failure prediction model establishing method and system as well as fan monitoring pre-warning system and method |
| CN103195727A (en) * | 2013-03-05 | 2013-07-10 | 天津理工大学 | Device for on-line monitoring and evaluating state of air blower |
| CN105136454A (en) * | 2015-10-15 | 2015-12-09 | 上海电机学院 | Wind turbine gear box fault recognition method |
| CN105787584A (en) * | 2016-01-28 | 2016-07-20 | 华北电力大学（保定） | Wind turbine malfunction early warning method based on cloud platform |
| CN106099932A (en) * | 2016-07-22 | 2016-11-09 | 中国电力科学研究院 | A kind of tidal current analysis method of plan a few days ago considering probabilistic temporal correlation |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103927695B (en) * | 2014-04-22 | 2017-11-24 | 国家电网公司 | Ultrashort-term wind power prediction method based on self study complex data source |
-
2017
- 2017-05-25 CN CN201710379893.9A patent/CN107147143B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102778358A (en) * | 2012-06-04 | 2012-11-14 | 上海东锐风电技术有限公司 | Failure prediction model establishing method and system as well as fan monitoring pre-warning system and method |
| CN103195727A (en) * | 2013-03-05 | 2013-07-10 | 天津理工大学 | Device for on-line monitoring and evaluating state of air blower |
| CN105136454A (en) * | 2015-10-15 | 2015-12-09 | 上海电机学院 | Wind turbine gear box fault recognition method |
| CN105787584A (en) * | 2016-01-28 | 2016-07-20 | 华北电力大学（保定） | Wind turbine malfunction early warning method based on cloud platform |
| CN106099932A (en) * | 2016-07-22 | 2016-11-09 | 中国电力科学研究院 | A kind of tidal current analysis method of plan a few days ago considering probabilistic temporal correlation |
Non-Patent Citations (2)
| Title |
|---|
| 基于SDP分析的离心风机失速检测及故障诊断研究;刘海啸;《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》;20170315;全文 * |
| 基于小波变换和数据挖掘的风电机在线故障诊断;王小鹏;《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》;20110415;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107147143A (en) | 2017-09-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Rafferty et al. | Real-time multiple event detection and classification using moving window PCA | |
| CN109633368A (en) | The method of duration power quality disturbances containing distributed power distribution network based on VMD and DFA | |
| CN107147143B (en) | Method for establishing early warning model of fan interlocking off-line fault | |
| CN110059845B (en) | Metering device clock error trend prediction method based on time sequence evolution gene model | |
| CN105372528B (en) | A kind of state maintenance method of Power Transformer Internal Faults and New Transformer | |
| CN112187528B (en) | Industrial control system communication flow online monitoring method based on SARIMA | |
| CN111337244B (en) | Method and device for monitoring and diagnosing faults of input shaft of fan gearbox | |
| CN111291918B (en) | Rotating machine degradation trend prediction method based on stationary subspace exogenous vector autoregression | |
| CN105137354A (en) | Motor fault detection method based on nerve network | |
| Ren et al. | Online anomaly detection using machine learning and HPC for power system synchrophasor measurements | |
| CN103699117A (en) | Method and system for diagnosing failure based on actual working conditions of nuclear power plant and simulation system | |
| Janczura et al. | Machine condition change detection based on data segmentation using a three-regime, α-stable Hidden Markov Model | |
| CN105629144B (en) | High-tension switch gear partial discharge diagnostic method and system based on fingerprint base | |
| CN116189802A (en) | Transformer fault early warning method based on gas concentration time sequence data | |
| Otudi et al. | Training Machine Learning Models with Simulated Data for Improved Line Fault Events Classification From 3-Phase PMU Field Recordings | |
| CN112697268B (en) | Motor anomaly detection integrated algorithm based on T-SNE | |
| CN108646124A (en) | A kind of oil chromatography online monitoring data variation tendency detection method based on small echo maximum | |
| CN110703080B (en) | GIS spike discharge diagnosis method, discharge degree identification method and device | |
| CN111814325A (en) | Single variable alarm threshold value optimization method for non-steady operation of coal-fired power generation equipment | |
| Amoateng et al. | An Intelligent Event Detection Framework To Improve Situational Awareness In PMU Power Distribution Networks | |
| JP7278499B1 (en) | LEARNING DEVICE, ANORMAL SIGNS DETECTION DEVICE, ANORMAL SIGNS DETECTION SYSTEM, LEARNING METHOD AND PROGRAM | |
| CN118096117B (en) | Digital twinning-based power equipment fault detection method and system | |
| CN117200458B (en) | Digital management method and device based on intelligent low-voltage switch cabinet | |
| CN112504435B (en) | High-voltage circuit breaker base screw loosening fault detection method | |
| Banasik et al. | Influence of wind speed on the reliability of low-voltage overhead power lines |
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 |