CN105158598A - Fault prediction method suitable for power equipment - Google Patents
Fault prediction method suitable for power equipment Download PDFInfo
- Publication number
- CN105158598A CN105158598A CN201510499496.6A CN201510499496A CN105158598A CN 105158598 A CN105158598 A CN 105158598A CN 201510499496 A CN201510499496 A CN 201510499496A CN 105158598 A CN105158598 A CN 105158598A
- Authority
- CN
- China
- Prior art keywords
- model
- power equipment
- sample
- sequence
- arma
- 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
- 238000000034 method Methods 0.000 title claims abstract description 31
- 241001123248 Arma Species 0.000 claims abstract description 78
- 238000012544 monitoring process Methods 0.000 claims abstract description 13
- 238000003745 diagnosis Methods 0.000 claims abstract description 11
- 238000005311 autocorrelation function Methods 0.000 claims description 12
- 238000012360 testing method Methods 0.000 claims description 9
- 206010019133 Hangover Diseases 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 5
- 238000005259 measurement Methods 0.000 claims description 4
- 230000008878 coupling Effects 0.000 claims description 3
- 238000010168 coupling process Methods 0.000 claims description 3
- 238000005859 coupling reaction Methods 0.000 claims description 3
- 230000001186 cumulative effect Effects 0.000 claims description 3
- 238000007689 inspection Methods 0.000 claims description 3
- 230000000750 progressive effect Effects 0.000 claims description 3
- 238000000926 separation method Methods 0.000 claims description 3
- 230000009897 systematic effect Effects 0.000 claims description 3
- 238000012795 verification Methods 0.000 claims description 3
- 238000012423 maintenance Methods 0.000 abstract description 8
- 230000002035 prolonged effect Effects 0.000 abstract 1
- 230000006870 function Effects 0.000 description 12
- 238000010801 machine learning Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000005284 excitation Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003449 preventive effect Effects 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a fault prediction method suitable for power equipment. The method comprises that (1) a sequence sample is established according to historical operation data, monitored online, of the power equipment; (2) the type of an ARMA model to which the sequence sample belongs is identified; (3) the order of the ARMA model whose type is determined is determined, and the amount of unknown parameters in the ARMA model is obtained; (4) values of the unknown parameters are estimated to establish the ARMA model initially; (5) whether the ARMA model established initially is valid is detected, if yes, establishment of the ARMA model is completed, and if no, the step (3) is returned to; and (6) operation data of the power equipment at any time in future is predicted according to the established ARMA model, and fault prediction and diagnosis are implemented. The fault prediction method is based on lots of historical monitoring data, the maintenance and using reliability of the power equipment are ensured, and the service life of the power equipment is prolonged.
Description
Technical field
The present invention relates to power domain, specifically a kind of failure prediction method being applicable to power equipment.
Background technology
In power industry, some equipment are had to be the main equipments maintaining operation of power networks, as the transformer of transformer station, the steam turbine, generator, excitation system etc. of power house, these equipment are cores of power utility plant, if broken down, not only can affect normally carrying out of enterprise's production, also will bring about great losses.The large-size steam turbine major accident of domestic and international generation is exactly representative instance.Therefore, in order to take preventive measures in time, avoid unnecessary loss, failure prediction be carried out to these nucleus equipments and has very important significance.
But along with the maximization of power system device, the increasing of complicated and operation power equipment, its running status constantly changes, implementing electrical equipment fault prediction is exactly in power equipment operational process or when substantially not dismantling with the task of diagnosis control, adopt various Measurement and analysis and method of discrimination, the historical situation of bonding apparatus and service condition, objective status residing for predict device, provides reliable basis for finding fault in advance and solving fault.
Summary of the invention
The object of the present invention is to provide a kind of failure prediction method being applicable to power equipment based on a large amount of Historical Monitoring data, sequence samples is set up after the history data of power equipment is screened, then arma modeling is set up, thus according to the arma modeling set up, failure prediction and diagnosis are carried out to the operation conditions of power equipment, make fault anticipation and maintenance measures more accurately and reliably; Ensure that the maintenance of power equipment and the reliability of use, extend the serviceable life of power equipment simultaneously.
For achieving the above object, the invention provides following technical scheme:
Be applicable to a failure prediction method for power equipment, comprise the following steps:
(1) sequence samples is set up according to the history data of the power equipment of on-line monitoring;
(2) type of the arma modeling belonging to recognition sequence sample;
(3) rank are determined to the arma modeling after determining affiliated type, obtain the number of the unknown parameter in arma modeling;
(4) estimate the parameter of the value of each unknown parameter, tentatively set up arma modeling;
(5) validity of the preliminary arma modeling set up of inspection; If model is effective, then arma modeling has been set up; If model is invalid, then return step (3);
(6) according to the service data of the arma modeling prediction power equipment of following any time set up, and failure prediction and diagnosis is made.
As the further scheme of the present invention: described step (1) comprising: carry out preliminary screening to the history data of the power equipment of on-line monitoring, the fault data of all vital electrical equipment after obtaining fault, and form sequence samples.
As the further scheme of the present invention: adopt WAMS system to carry out preliminary screening to the history data of the power equipment of on-line monitoring.
As the further scheme of the present invention: the topological relation between described step (1) also comprises according to power equipment, the historical data of power equipment is successively classified according to physical couplings, be divided into the equipment that range connects for N time.
As the further scheme of the present invention: described step (2) comprising:
21) coefficient of autocorrelation of sample sequence is calculated;
Wherein,
represent spacing be k sample coefficient of autocorrelation, n represents total sample number, t represents sample sequence number, k represents two sample separation, x represents sample average, x
trepresent sample sequence;
22) PARCOR coefficients of described sample sequence are calculated;
，
Wherein,
represent sample sequence PARCOR coefficients,
for auto-covariance function,
for variance function:
23) type identifying the arma modeling belonging to sample sequence according to coefficient of autocorrelation and PARCOR coefficients is autoregressive model, moving average model(MA model) or ARMA model.
As the further scheme of the present invention: described step 23) comprising: the coefficient of autocorrelation of sample sequence is substituted into the stationary sequence { y in arma modeling
tin autocorrelation function in, the PARCOR coefficients of sample sequence are substituted into the stationary sequence { y in arma modeling
tin deviation―related function in;
If stationary sequence { y
tin deviation―related function be truncation, autocorrelation function be hangover, then described sample sequence is identified as autoregressive model;
If described stationary sequence { y
tdeviation―related function be hangover, autocorrelation function is truncation, then sample sequence is identified as moving average model(MA model);
If stationary sequence { y
tdeviation―related function and autocorrelation function be all trail, then sample sequence is identified as ARMA model.
As the further scheme of the present invention: the rank of determining of described step (3) are: according to exploratory rule, to the rank (p, q) of the arma modeling determined after affiliated type by low order to the progressive determination of high-order, it comprises:
Suppose H
o: Φ
p=0, θ
α=0; Then when total sample number n is fully large,
Statistic
in, given insolation level α, can obtain F by F (2, n-p-q)
αvalue, n>=p+q > 2;
If F<Fa, then suppose H
oset up, namely the rank of ARMA model are (p-1, q-1), complete and determine rank;
If F>=Fa, then suppose H
obe false, the higher exponent number of selected ARMA model, determines rank again;
Wherein, H
ofor the residual sum of squares (RSS) that the hypothesis parameter of the proposition in test of hypothesis, Q are ARMA (p, q), Q ' is the residual sum of squares (RSS) of ARMA (p-1, q-1); F be statistic,
Φ pundetermined coefficient, θ when exponent number for autoregressive model is p
αundetermined coefficient when exponent number for moving average model(MA model) is q.
As the further scheme of the present invention: the method estimated the unknown parameter in the ARMA model of the sequence samples identified in described step (4) is the least square estimation method, and it comprises:
；
Wherein, μ is sample average, the disturbance ε of arma modeling
tmeet independent Gaussian distribution
,
Φ p(B)=1-
Φ 0-
Φ 1b-...-
Φ pb
pfor p rank autoregressive coefficient polynomial expression, θ
q(B)=1-θ
1b-θ
2b
2-...-θ
qb
qfor q rank moving average coefficient polynomial expression, B
qfor q rank delay operator,
Φ 0,
Φ 1......
Φ pfor autoregressive model parameter to be estimated, θ
1, θ
2θ
qfor moving average model(MA model) parameter to be estimated; x
tfor sample sequence;
Bx
t=X
t-1；
Wherein, B represents delay operator;
B
px
t=X
t-preverse form in conjunction with arma modeling is:
；
Suppose: x
t=o, t≤o;
Then according to condition least square method criterion:
;
Wherein, X
t-1for the time be the sample in t-1 moment, t is sample sequence number, i is cumulative measurement parameter, B in formula
pfor p rank delay operator, X
t-Pfor sample, X that the time is the t-i moment
t-ifor the time be the t-i moment sample,
for the systematic error that Least square-fit is asked for;
When
when getting minimum value, namely
, right
Φ 0,
Φ 1......
Φ p, θ
1, θ
2θ
qask for partial derivative respectively, namely try to achieve the estimated value of p+q described unknown parameter.
As the further scheme of the present invention: described step (5) comprising:
51) whether the residual error checking arma modeling is purely random sequence, if so, then after model of fit, does white noise verification to residual error; If not, then return step (3) and again determine rank;
52) if be white noise to residual test result display residual error, then model is effective, and then carries out fault diagnosis according to the predicted data of model to power equipment; If be white noise to residual test result display residual error, then illustrate that model is invalid, return step (3) and again determine rank.
Compared with prior art, the invention has the beneficial effects as follows:
The present invention is based on a large amount of Historical Monitoring data, after the history data of power equipment is screened, set up sequence samples, then the type of the arma modeling described in sequence samples identified and determine rank, thus setting up arma modeling; Through checking effectively, the arma modeling according to setting up carries out failure prediction and diagnosis to the operation conditions of power equipment.The present invention embodies the individual character of power equipment, react power equipment running state characteristic over time, make the forecast model that it is set up compared to tradition according to machine learning, more stable, thus improve the accuracy of the on-line operation data prediction of power equipment, make fault anticipation and maintenance measures more accurately and reliably; Ensure that the maintenance of power equipment and the reliability of use, extend the serviceable life of power equipment simultaneously.
Accompanying drawing explanation
Fig. 1 is the process flow diagram of the failure prediction method being applicable to power equipment.
Embodiment
Below in conjunction with the embodiment of the present invention, be clearly and completely described the technical scheme in the embodiment of the present invention, obviously, described embodiment is only the present invention's part embodiment, instead of whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art, not making the every other embodiment obtained under creative work prerequisite, belong to the scope of protection of the invention.
Refer to Fig. 1, in the embodiment of the present invention, a kind of failure prediction method being applicable to power equipment, comprises the following steps:
(1) sequence samples is set up according to the history data of the power equipment of on-line monitoring.
Step (1) comprising: adopt WAMS system to carry out preliminary screening to the history data of the power equipment of on-line monitoring, the fault data of all vital electrical equipment after obtaining fault, and form sequence samples.And according to the topological relation between power equipment, the historical data of power equipment is successively classified according to physical couplings, be divided into the equipment that range connects for N time.
(2) type of the arma modeling belonging to recognition sequence sample.
Step (2) comprising:
21) coefficient of autocorrelation of sample sequence is calculated;
Wherein,
represent spacing be k sample coefficient of autocorrelation, n represents total sample number, t represents sample sequence number, k represents two sample separation, x represents sample average, x
trepresent sample sequence;
22) PARCOR coefficients of described sample sequence are calculated;
，
Wherein,
represent sample sequence PARCOR coefficients,
for auto-covariance function,
for variance function:
23) type identifying the arma modeling belonging to sample sequence according to coefficient of autocorrelation and PARCOR coefficients is autoregressive model, moving average model(MA model) or ARMA model.
Step 23) comprising: the coefficient of autocorrelation of sample sequence is substituted into the stationary sequence { y in arma modeling
tin autocorrelation function in, the PARCOR coefficients of sample sequence are substituted into the stationary sequence { y in arma modeling
tin deviation―related function in;
If stationary sequence { y
tin deviation―related function be truncation, autocorrelation function be hangover, then described sample sequence is identified as autoregressive model;
If described stationary sequence { y
tdeviation―related function be hangover, autocorrelation function is truncation, then sample sequence is identified as moving average model(MA model);
If stationary sequence { y
tdeviation―related function and autocorrelation function be all trail, then sample sequence is identified as ARMA model.
(3) rank are determined to the arma modeling after determining affiliated type, obtain the number of the unknown parameter in arma modeling.
The rank of determining of step (3) are: according to exploratory rule, to the rank (p, q) of the arma modeling determined after affiliated type by low order to the progressive determination of high-order, it comprises:
Suppose H
o: Φ
p=0, θ
α=0; Then when total sample number n is fully large,
Statistic
in, given insolation level α, can obtain F by F (2, n-p-q)
αvalue, n>=p+q > 2;
If F<Fa, then suppose H
oset up, namely the rank of ARMA model are (p-1, q-1), complete and determine rank;
If F>=Fa, then suppose H
obe false, the higher exponent number of selected ARMA model, determines rank again;
Wherein, H
ofor the residual sum of squares (RSS) that the hypothesis parameter of the proposition in test of hypothesis, Q are ARMA (p, q), Q ' is the residual sum of squares (RSS) of ARMA (p-1, q-1); F be statistic,
Φ pundetermined coefficient, θ when exponent number for autoregressive model is p
αundetermined coefficient when exponent number for moving average model(MA model) is q.
(4) estimate the parameter of the value of each unknown parameter, tentatively set up arma modeling.
The method estimated the unknown parameter in the ARMA model of the sequence samples identified in step (4) is the least square estimation method, and it comprises:
；
Wherein, μ is sample average, the disturbance ε of arma modeling
tmeet independent Gaussian distribution
,
Φ p(B)=1-
Φ 0-
Φ 1b-...-
Φ pb
pfor p rank autoregressive coefficient polynomial expression, θ
q(B)=1-θ
1b-θ
2b
2-...-θ
qb
qfor q rank moving average coefficient polynomial expression, B
qfor q rank delay operator,
Φ 0,
Φ 1......
Φ pfor autoregressive model parameter to be estimated, θ
1, θ
2θ
qfor moving average model(MA model) parameter to be estimated; x
tfor sample sequence;
Bx
t=X
t-1；
Wherein, B represents delay operator;
B
px
t=X
t-preverse form in conjunction with arma modeling is:
；
Suppose: x
t=o, t≤o;
Then according to condition least square method criterion:
;
Wherein, X
t-1for the time be the sample in t-1 moment, t is sample sequence number, i is cumulative measurement parameter, B in formula
pfor p rank delay operator, X
t-Pfor sample, X that the time is the t-i moment
t-ifor the time be the t-i moment sample,
for the systematic error that Least square-fit is asked for;
When
when getting minimum value, namely
, right
Φ 0,
Φ 1......
Φ p, θ
1, θ
2θ
qask for partial derivative respectively, namely try to achieve the estimated value of p+q described unknown parameter.
(5) validity of the preliminary arma modeling set up of inspection; If model is effective, then arma modeling has been set up; If model is invalid, then return step (3).
Step (5) comprising:
51) whether the residual error checking arma modeling is purely random sequence, if so, then after model of fit, does white noise verification to residual error; If not, then return step (3) and again determine rank;
52) if be white noise to residual test result display residual error, then model is effective, and then carries out fault diagnosis according to the predicted data of model to power equipment; If be white noise to residual test result display residual error, then illustrate that model is invalid, return step (3) and again determine rank.
(6) according to the service data of the arma modeling prediction power equipment of following any time set up, and failure prediction and diagnosis is made.According to failure prediction and diagnostic result, strengthen the operation monitoring to power equipment, and to its maintenance or replacing.
The present invention is based on a large amount of Historical Monitoring data, after the history data of power equipment is screened, set up sequence samples, then the type of the arma modeling described in sequence samples identified and determine rank, thus setting up arma modeling; Through checking effectively, the arma modeling according to setting up carries out failure prediction and diagnosis to the operation conditions of power equipment.The present invention embodies the individual character of power equipment, react power equipment running state characteristic over time, make the forecast model that it is set up compared to tradition according to machine learning, more stable, thus improve the accuracy of the on-line operation data prediction of power equipment, make fault anticipation and maintenance measures more accurately and reliably; Ensure that the maintenance of power equipment and the reliability of use, extend the serviceable life of power equipment simultaneously.
To those skilled in the art, obviously the invention is not restricted to the details of above-mentioned one exemplary embodiment, and when not deviating from spirit of the present invention or essential characteristic, the present invention can be realized in other specific forms.Therefore, no matter from which point, all should embodiment be regarded as exemplary, and be nonrestrictive, scope of the present invention is limited by claims instead of above-mentioned explanation, and all changes be therefore intended in the implication of the equivalency by dropping on claim and scope are included in the present invention.
In addition, be to be understood that, although this instructions is described according to embodiment, but not each embodiment only comprises an independently technical scheme, this narrating mode of instructions is only for clarity sake, those skilled in the art should by instructions integrally, and the technical scheme in each embodiment also through appropriately combined, can form other embodiments that it will be appreciated by those skilled in the art that.
Claims (9)
1. be applicable to a failure prediction method for power equipment, it is characterized in that, comprise the following steps:
(1) sequence samples is set up according to the history data of the power equipment of on-line monitoring;
(2) type of the arma modeling belonging to recognition sequence sample;
(3) rank are determined to the arma modeling after determining affiliated type, obtain the number of the unknown parameter in arma modeling;
(4) estimate the parameter of the value of each unknown parameter, tentatively set up arma modeling;
(5) validity of the preliminary arma modeling set up of inspection; If model is effective, then arma modeling has been set up; If model is invalid, then return step (3);
(6) according to the service data of the arma modeling prediction power equipment of following any time set up, and failure prediction and diagnosis is made.
2. the failure prediction method being applicable to power equipment according to claim 1, it is characterized in that, described step (1) comprising: carry out preliminary screening to the history data of the power equipment of on-line monitoring, the fault data of all vital electrical equipment after obtaining fault, and form sequence samples.
3. the failure prediction method being applicable to power equipment according to claim 2, is characterized in that, adopts WAMS system to carry out preliminary screening to the history data of the power equipment of on-line monitoring.
4. the failure prediction method being applicable to power equipment according to claim 2, it is characterized in that, topological relation between described step (1) also comprises according to power equipment, successively classifies the historical data of power equipment according to physical couplings, is divided into the equipment that range connects for N time.
5. the failure prediction method being applicable to power equipment according to claim 1, is characterized in that, described step (2) comprising:
21) coefficient of autocorrelation of sample sequence is calculated;
Wherein,
represent spacing be k sample coefficient of autocorrelation, n represents total sample number, t represents sample sequence number, k represents two sample separation, x represents sample average, x
trepresent sample sequence;
22) PARCOR coefficients of described sample sequence are calculated;
，
Wherein,
represent sample sequence PARCOR coefficients,
for auto-covariance function,
for variance function:
23) type identifying the arma modeling belonging to sample sequence according to coefficient of autocorrelation and PARCOR coefficients is autoregressive model, moving average model(MA model) or ARMA model.
6. the failure prediction method being applicable to power equipment according to claim 5, is characterized in that, described step 23) comprising: the coefficient of autocorrelation of sample sequence is substituted into the stationary sequence { y in arma modeling
tin autocorrelation function in, the PARCOR coefficients of sample sequence are substituted into the stationary sequence { y in arma modeling
tin deviation―related function in;
If stationary sequence { y
tin deviation―related function be truncation, autocorrelation function be hangover, then described sample sequence is identified as autoregressive model;
If described stationary sequence { y
tdeviation―related function be hangover, autocorrelation function is truncation, then sample sequence is identified as moving average model(MA model);
If stationary sequence { y
tdeviation―related function and autocorrelation function be all trail, then sample sequence is identified as ARMA model.
7. the failure prediction method being applicable to power equipment according to claim 1, it is characterized in that, the rank of determining of described step (3) are: according to exploratory rule, to the rank (p of the arma modeling determined after affiliated type, q) by low order to the progressive determination of high-order, it comprises:
Suppose H
o: Φ
p=0, θ
α=0; Then when total sample number n is fully large,
Statistic
in, given insolation level α, can obtain F by F (2, n-p-q)
αvalue, n>=p+q > 2;
If F<Fa, then suppose H
oset up, namely the rank of ARMA model are (p-1, q-1), complete and determine rank;
If F>=Fa, then suppose H
obe false, the higher exponent number of selected ARMA model, determines rank again;
Wherein, H
ofor the residual sum of squares (RSS) that the hypothesis parameter of the proposition in test of hypothesis, Q are ARMA (p, q), Q ' is the residual sum of squares (RSS) of ARMA (p-1, q-1); F be statistic,
Φ pundetermined coefficient, θ when exponent number for autoregressive model is p
αundetermined coefficient when exponent number for moving average model(MA model) is q.
8. the failure prediction method being applicable to power equipment according to claim 1, it is characterized in that, the method estimated the unknown parameter in the ARMA model of the sequence samples identified in described step (4) is the least square estimation method, and it comprises:
；
Wherein, μ is sample average, the disturbance ε of arma modeling
tmeet independent Gaussian distribution
,
Φ p(B)=1-
Φ 0-
Φ 1b-...-
Φ pb
pfor p rank autoregressive coefficient polynomial expression, θ
q(B)=1-θ
1b-θ
2b
2-...-θ
qb
qfor q rank moving average coefficient polynomial expression, B
qfor q rank delay operator,
Φ 0,
Φ 1......
Φ pfor autoregressive model parameter to be estimated, θ
1, θ
2θ
qfor moving average model(MA model) parameter to be estimated; x
tfor sample sequence;
Bx
t=X
t-1；
Wherein, B represents delay operator;
B
px
t=X
t-preverse form in conjunction with arma modeling is:
；
Suppose: x
t=o, t≤o;
Then according to condition least square method criterion:
;
Wherein, X
t-1for the time be the sample in t-1 moment, t is sample sequence number, i is cumulative measurement parameter, B in formula
pfor p rank delay operator, X
t-Pfor sample, X that the time is the t-i moment
t-ifor the time be the t-i moment sample,
for the systematic error that Least square-fit is asked for;
When
when getting minimum value, namely
, right
Φ 0,
Φ 1......
Φ p, θ
1, θ
2θ
qask for partial derivative respectively, namely try to achieve the estimated value of p+q described unknown parameter.
9. the failure prediction method being applicable to power equipment according to claim 1, is characterized in that, described step (5) comprising:
51) whether the residual error checking arma modeling is purely random sequence, if so, then after model of fit, does white noise verification to residual error; If not, then return step (3) and again determine rank;
52) if be white noise to residual test result display residual error, then model is effective, and then carries out fault diagnosis according to the predicted data of model to power equipment; If be white noise to residual test result display residual error, then illustrate that model is invalid, return step (3) and again determine rank.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510499496.6A CN105158598A (en) | 2015-08-15 | 2015-08-15 | Fault prediction method suitable for power equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510499496.6A CN105158598A (en) | 2015-08-15 | 2015-08-15 | Fault prediction method suitable for power equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105158598A true CN105158598A (en) | 2015-12-16 |
Family
ID=54799518
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510499496.6A Pending CN105158598A (en) | 2015-08-15 | 2015-08-15 | Fault prediction method suitable for power equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105158598A (en) |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105631596A (en) * | 2015-12-29 | 2016-06-01 | 山东鲁能软件技术有限公司 | Equipment fault diagnosis method based on multidimensional segmentation fitting |
| CN105760672A (en) * | 2016-02-22 | 2016-07-13 | 江苏科技大学 | Diagnosis method for mechanical equipment faults |
| CN106598029A (en) * | 2016-12-21 | 2017-04-26 | 北京交通大学 | Train control vehicle equipment reliability prediction method based on performance degeneration |
| CN107085750A (en) * | 2017-03-10 | 2017-08-22 | 广东工业大学 | A kind of mixing dynamic fault Forecasting Methodology based on ARMA and ANN |
| CN107247198A (en) * | 2017-05-09 | 2017-10-13 | 安徽继远软件有限公司 | A kind of distribution equipment malfunction Forecasting Methodology and device |
| CN108573275A (en) * | 2018-03-07 | 2018-09-25 | 浙江大学 | A kind of construction method of online classification micro services |
| CN108646139A (en) * | 2018-05-15 | 2018-10-12 | 四川蓉电科技发展有限公司 | A kind of 10KV circuits O＆M power failure precise positioning method |
| CN108923422A (en) * | 2018-07-13 | 2018-11-30 | 全球能源互联网研究院有限公司 | Internet of Things proxy data processing method, system and electric network terminal equipment monitoring system |
| CN109447512A (en) * | 2018-11-13 | 2019-03-08 | 重庆大学 | Bulk power grid reliability estimation method based on uniform design |
| CN109540808A (en) * | 2018-11-02 | 2019-03-29 | 湖南文理学院 | A kind of transformer detection system and method for diagnosing faults |
| CN109614742A (en) * | 2018-12-25 | 2019-04-12 | 中国海洋大学 | A kind of sea level height duration prediction algorithm |
| CN110209999A (en) * | 2018-02-28 | 2019-09-06 | 广州地铁集团有限公司 | A kind of mobile unit failure trend prediction method |
| CN110836783A (en) * | 2019-10-29 | 2020-02-25 | 杭州电子科技大学 | GA-BP magnetic suspension train fault detection method based on threshold judgment |
| CN111126656A (en) * | 2019-11-10 | 2020-05-08 | 国网浙江省电力有限公司温州供电公司 | Electric energy meter fault quantity prediction method |
| CN111682532A (en) * | 2020-06-12 | 2020-09-18 | 国网重庆市电力公司电力科学研究院 | Excitation system uncompensated phase-frequency characteristic online modeling method and storage medium |
| CN111813822A (en) * | 2020-05-25 | 2020-10-23 | 国网河南省电力公司 | Method and system for determining polynomial fitting node voltage effective value based on WANS |
| CN111929489A (en) * | 2020-08-18 | 2020-11-13 | 电子科技大学 | Fault arc current detection method and system |
| CN113742932A (en) * | 2021-09-13 | 2021-12-03 | 华能新能源股份有限公司 | Method for predicting and diagnosing faults of gearbox of wind turbine generator |
-
2015
- 2015-08-15 CN CN201510499496.6A patent/CN105158598A/en active Pending
Cited By (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105631596A (en) * | 2015-12-29 | 2016-06-01 | 山东鲁能软件技术有限公司 | Equipment fault diagnosis method based on multidimensional segmentation fitting |
| CN105631596B (en) * | 2015-12-29 | 2020-12-29 | 山东鲁能软件技术有限公司 | Equipment fault diagnosis method based on multi-dimensional piecewise fitting |
| CN105760672A (en) * | 2016-02-22 | 2016-07-13 | 江苏科技大学 | Diagnosis method for mechanical equipment faults |
| CN105760672B (en) * | 2016-02-22 | 2018-04-24 | 江苏科技大学 | A kind of Trouble Diagnostic Method of Machinery Equipment |
| CN106598029A (en) * | 2016-12-21 | 2017-04-26 | 北京交通大学 | Train control vehicle equipment reliability prediction method based on performance degeneration |
| CN107085750A (en) * | 2017-03-10 | 2017-08-22 | 广东工业大学 | A kind of mixing dynamic fault Forecasting Methodology based on ARMA and ANN |
| CN107247198A (en) * | 2017-05-09 | 2017-10-13 | 安徽继远软件有限公司 | A kind of distribution equipment malfunction Forecasting Methodology and device |
| CN110209999A (en) * | 2018-02-28 | 2019-09-06 | 广州地铁集团有限公司 | A kind of mobile unit failure trend prediction method |
| CN108573275A (en) * | 2018-03-07 | 2018-09-25 | 浙江大学 | A kind of construction method of online classification micro services |
| CN108573275B (en) * | 2018-03-07 | 2020-08-25 | 浙江大学 | Construction method of online classification micro-service |
| CN108646139A (en) * | 2018-05-15 | 2018-10-12 | 四川蓉电科技发展有限公司 | A kind of 10KV circuits O＆M power failure precise positioning method |
| CN108923422A (en) * | 2018-07-13 | 2018-11-30 | 全球能源互联网研究院有限公司 | Internet of Things proxy data processing method, system and electric network terminal equipment monitoring system |
| CN109540808A (en) * | 2018-11-02 | 2019-03-29 | 湖南文理学院 | A kind of transformer detection system and method for diagnosing faults |
| CN109447512A (en) * | 2018-11-13 | 2019-03-08 | 重庆大学 | Bulk power grid reliability estimation method based on uniform design |
| CN109447512B (en) * | 2018-11-13 | 2021-12-03 | 重庆大学 | Large power grid reliability assessment method based on uniform design |
| CN109614742A (en) * | 2018-12-25 | 2019-04-12 | 中国海洋大学 | A kind of sea level height duration prediction algorithm |
| CN110836783A (en) * | 2019-10-29 | 2020-02-25 | 杭州电子科技大学 | GA-BP magnetic suspension train fault detection method based on threshold judgment |
| CN111126656A (en) * | 2019-11-10 | 2020-05-08 | 国网浙江省电力有限公司温州供电公司 | Electric energy meter fault quantity prediction method |
| CN111126656B (en) * | 2019-11-10 | 2023-07-04 | 国网浙江省电力有限公司温州供电公司 | Electric energy meter fault quantity prediction method |
| CN111813822A (en) * | 2020-05-25 | 2020-10-23 | 国网河南省电力公司 | Method and system for determining polynomial fitting node voltage effective value based on WANS |
| CN111682532A (en) * | 2020-06-12 | 2020-09-18 | 国网重庆市电力公司电力科学研究院 | Excitation system uncompensated phase-frequency characteristic online modeling method and storage medium |
| CN111929489A (en) * | 2020-08-18 | 2020-11-13 | 电子科技大学 | Fault arc current detection method and system |
| CN111929489B (en) * | 2020-08-18 | 2021-12-28 | 电子科技大学 | Fault arc current detection method and system |
| CN113742932A (en) * | 2021-09-13 | 2021-12-03 | 华能新能源股份有限公司 | Method for predicting and diagnosing faults of gearbox of wind turbine generator |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105158598A (en) | Fault prediction method suitable for power equipment | |
| CN104820146A (en) | Transformer fault prediction method based on monitoring data of dissolved gas in oil of transformer | |
| CN109583520B (en) | State evaluation method of cloud model and genetic algorithm optimization support vector machine | |
| CN106019195B (en) | Electric power measurement automation verification assembly line fault diagnosis system | |
| CN104390657B (en) | A kind of Generator Unit Operating Parameters measurement sensor fault diagnosis method and system | |
| CN103400310B (en) | Method for evaluating power distribution network electrical equipment state based on historical data trend prediction | |
| CN106873571B (en) | early warning method based on data and model fusion | |
| CN113935439B (en) | Fault detection method, equipment, server and storage medium for drainage pipe network | |
| CN107944571B (en) | Method for predicting residual service life of power transformer | |
| CN106407589B (en) | Fan state evaluation and prediction method and system | |
| CN106059496B (en) | A kind of photovoltaic module array performance monitoring and the method and system of Fault Identification | |
| CN105866638A (en) | City network cable joint insulation state online monitoring apparatus early warning apparatus and method | |
| CN109613428A (en) | It is a kind of can be as system and its application in motor device fault detection method | |
| CN112799898B (en) | Interconnection system fault node positioning method and system based on distributed fault detection | |
| CN104537487A (en) | Assessment method of operating dynamic risk of electric transmission and transformation equipment | |
| CN104318347A (en) | Power transmission line icing state assessment method based on information fusion of multiple sensors | |
| CN104200396A (en) | Wind driven generator part fault early warning method | |
| CN106483847B (en) | A kind of water cooler fault detection method based on adaptive ICA | |
| CN105719094A (en) | State evaluation method of power transmission equipment | |
| CN102868224B (en) | Secondary network measurement and multimode decision-making method and device for intelligent substation | |
| CN106786531B (en) | Power distribution terminal optimal configuration method | |
| CN105404280A (en) | Industrial process fault detection method based on autoregression dynamic hidden variable model | |
| CN106569052A (en) | Real-time health status-considered method for evaluating reliability of power transformer | |
| CN113239132A (en) | Online out-of-tolerance identification method for voltage transformer | |
| CN107247198A (en) | A kind of distribution equipment malfunction Forecasting Methodology and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20151216 |