CN102411106A - Fault monitoring method and device for power transformer - Google Patents
Fault monitoring method and device for power transformer Download PDFInfo
- Publication number
- CN102411106A CN102411106A CN2011103706836A CN201110370683A CN102411106A CN 102411106 A CN102411106 A CN 102411106A CN 2011103706836 A CN2011103706836 A CN 2011103706836A CN 201110370683 A CN201110370683 A CN 201110370683A CN 102411106 A CN102411106 A CN 102411106A
- Authority
- CN
- China
- Prior art keywords
- fault
- transformer
- data
- power transformer
- posterior probability
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Landscapes
- Testing Electric Properties And Detecting Electric Faults (AREA)
- Housings And Mounting Of Transformers (AREA)
Abstract
The invention provides a fault monitoring method and device for a power transformer. The method comprises the following steps of: performing characteristic quantity extraction and compression on a polynary monitoring variable; computing the probability distribution function of a characteristic quantity in normal running and fault modes of the transformer; and updating a posterior probability function in real time according to newly-monitored data and performing fault classification according to a posterior probability. According to the method and the device provided by the invention, the health condition of the transformer can be judged by using monitoring data of the transformer, potential faults and the fault development trend can be found in time, and the aims of lowering accident occurrence rate and saving maintenance cost are fulfilled.
Description
Technical field
The present invention relates to electric system, relate in particular to a kind of power transformer fault monitoring method and a kind of power transformer fault monitoring device.
Background technology
Power transformer is the nucleus equipment of electric power networks, and the health status of transformer and life cycle are very crucial to the power grid security reliability service.In the transformer operational process, effectively transformer is carried out fault diagnosis, judge the running status of transformer and the development trend of fault exactly, help producers' plan of scientifically arranging production, the generation of minimizing accident.
Transformer owing to the influence of voltage, heat, chemistry, mechanical vibration and other factors, the phenomenon of insulation ag(e)ing, material deterioration occurs in the process of long-time running, and outside destruction and influence etc., causes the transformer fault accident unavoidably.Simultaneously, possibly there are some quality problems in transformer in the process of design and manufacturing, and in installation process, also possibly occur damaging, and will cause some latency faults thus.
The method of artificial intelligence is mainly adopted in the quantitative test of current transformer state, and wherein modal is artificial neural network and expert system.(Artificial Neural Networks ANN) has very strong self-learning capability to artificial neural network, can realize approaching any complex nonlinear function in theory.The Multi-layered Feedforward Networks of using back-propagation algorithm is maximum a kind of neural network form of in pattern-recognition and fault diagnosis, using at present.But the neural network of backpropagation is faced with many difficult problems in practical engineering application: at first be that the structure of neural network and the quantity of node are not easy to confirm; Next is that speed of convergence is slow in the neural metwork training process.And a large amount of historical datas of the common needs of the training process of neural network, the fault data that can produce in the reality often occupies the minority, and the structure and parameter of neural network often lacks the actual physical meaning in addition, is unfavorable for debugging and improvement.Above-mentioned these problems all influenced artificial neural network the physical fault diagnosis in effect.Expert system (Expert System) is another kind of artificial intelligence approach commonly used, and it is through combining the simulation field expert to solve challenge professional knowledge and reasoning from logic.But the foundation of expert system needs a large amount of practical experiences, and is difficult to surmount these experiences and directly from historical data, excavates out rule.In addition, the quantity of rule increases with the variable number exponentially in the expert system, when " shot array " effect possibly appear in variable number more for a long time, needs huge calculated amount.
In addition, along with the continuous progress of theoretical research, statistical Data Mining and random process model are applied to the state analysis and the auxiliary maintenance decision of complex device in recent years gradually.Compare with intelligent algorithm, it has many advantages:
At first, this class model takes in the time as an important factor, with the development differentiation of dynamic angle research system; And traditional neural networks and expert system only are confined to analyze feature mode stable or transient state.Because the appearance of the degeneration of transformer performance, fault and development all are dynamic processes, and " remaining life " also be a time quantum, therefore must adopt the analytical approach of stochastic process could hold its dynamic perfromance exactly.
Secondly; The method of analysis of statistical data can be analyzed small sample data and missing data effectively; At condition monitoring system initial operating stage data imperfection or when having misdata, can utilize available data substantially, and calculated amount is significantly less than intelligent algorithm.In addition, statistical models also has more accurate predictive ability and clear physical meaning more.
In recent years, statistical Data Mining and random process model have obtained significant effect in machinery maintenance optimization field.But the operation of electric system and aging has bigger singularity; Main-transformer as the electric system visual plant often also has higher standard in reliability and security, therefore, and in power grid enterprises' construction " intelligent grid " under the new situation; How to research and develop out as soon as possible state analysis and prediction algorithm to main-transformer; Scientifically arrange the transformer maintenance schedule with the personnel of maintaining easily, the minimizing accident takes place and practices thrift maintenance cost, becomes problem demanding prompt solution.
Summary of the invention
For addressing the above problem; The present invention provides a kind of power transformer fault monitoring method and device, can in time find latent transformer fault and fault progression trend, scientifically arranges the transformer maintenance schedule thereby help the maintainer; Maintenance cost is practiced thrift in the generation of minimizing accident.
For achieving the above object, the present invention adopts following technical scheme:
A kind of power transformer fault monitoring method comprises the steps:
Polynary monitored parameters is carried out Characteristic Extraction and compression;
The probability distribution function of calculated characteristics amount under transformer normal operation and fault mode;
Upgrade the posterior probability function according to the data in real time that newly monitors, and carry out failure modes according to posterior probability.
A kind of power transformer fault monitoring device comprises:
The Characteristic Extraction module is used for polynary monitored parameters is carried out Characteristic Extraction and compression;
The function calculation module is used for the probability distribution function of calculated characteristics amount under transformer normal operation and fault mode;
The failure modes module is used for upgrading the posterior probability function according to the data in real time that newly monitors, and carries out failure modes according to posterior probability.
Can find out by above scheme; Power transformer fault monitoring method of the present invention and device; It at first carries out pre-service through statistical model to data, and then calculating transformer is in the probability of malfunction, realizes the classification and the monitoring of fault through posterior probability.Method of the present invention and device can utilize the transformer monitoring data to judge the health status of transformer; In time find latency fault and fault progression trend; Replace scheduled overhaul with repair based on condition of component, thereby reach the generation of minimizing accident, the purpose of saving maintenance cost.
Description of drawings
Fig. 1 is the schematic flow sheet of power transformer fault monitoring method of the present invention;
Fig. 2 is the structural representation of power transformer fault monitoring device of the present invention.
Embodiment
The present invention provides a kind of power transformer fault monitoring method and device, can solve in the prior art and can't in time find the high problem of maintenance cost that latent transformer fault and fault progression trend are brought.Below in conjunction with accompanying drawing, the present invention is done further detailed explanation.
As shown in Figure 1, power transformer fault monitoring method of the present invention comprises the steps:
Step S1 carries out Characteristic Extraction and compression to polynary monitored parameters.This process specifically can comprise: come polynary monitored parameters is carried out Characteristic Extraction and compression through PLS PLS, extract the Useful Information of model, remove redundant information, make algorithm efficient, fast.The universal model of said PLS is:
X=TP
T+E
Y=TQ
T+F; (1)
Wherein, X is the oil chromatography data matrix of transformer monitoring, and the behavior observation time is classified gas projects as; Y is the indicating fault variable, is 0 and 1 to the training data value; T is a weighting coefficient matrix; P and Q are the loading matrix; E and F are the error vector of multivariate normal distribution.Through this step can be " decision variable " Y of an one dimension with the transformer oil chromatographic data-switching of multidimensional.
As an embodiment preferably, before step S1, can comprise step S0: original test data is cleared up, and filtering extracts the useful information directly related with transformer health status from the interference of external factor such as environment, load.This process specifically can comprise: the vectorial auto-regressive time series model VARX through supplementary variable comes original test data is cleared up.The normal structure of said VARX model is:
Wherein, X
tThe oil chromatography data of table t transformer monitoring constantly, X
T-iBe the oil chromatography data of t-i transformer monitoring constantly, ε
tBe t random disturbance constantly, d
T-iBe t-i external interference data constantly.If load data and Monitoring Data are not complementary in the reality, then can carry out interpolation to point of proximity.To obtaining the situation of satisfied coupling, then can skip over this step S0, directly use raw data to carry out the operation of next step (step S1).
Step S2, the probability distribution function of calculated characteristics amount under transformer normal operation and fault mode.This process specifically can comprise: output data Y is carried out histogram analysis; Fault is divided into overheating fault and discharge fault two big classifications; The basic distribution situation of Y value when judging all kinds of faults with normal operation; Use normal distribution that these histograms are fitted, obtain the distribution function h under the malfunction
1(z), the distribution function h under the normal condition
2(z); Wherein, h
1(z) be divided into two classifications again: the distribution function h of Y under the overheated condition
1The distribution function h of Y under o (z), the discharging condition
1D (z).
Step S3 upgrades the posterior probability function according to the data in real time that newly monitors, and carries out failure modes according to posterior probability.This process specifically can comprise as follows:
Step S301 uses Monitoring Data Y to come update system state X, can utilize Bayesian formula to realize:
Step S302 utilizes by the end of all historical datas of present moment t=mh and comes computing system to be in the posterior probability P of malfunction, to carry out fault diagnosis and maintenance decision; Wherein, h is the SI, and m is by the end of t sampling total degree constantly; Come more new model that following formula is used in the judgement of system failure state according to the value that newly observes then:
P
t=1-(1-P
Mh) e
-θ (t-mh), to the h of mh<t<(m+1);
Step S303 is on the basis of Bayes's posterior probability, according to the distribution function h under the said normal condition
2(z), the distribution function h of Y under the overheating fault condition
1o(z), the distribution function h of Y under the discharge fault condition
1d(z), calculate system and be in posterior probability P overheated, discharge
oAnd P
d, carry out failure modes, for example: if P
o>P
d, then system is in overheating fault.
Information with extracting is upgraded priori; Form with prior probability is represented; Net result is through the form output of posterior probability vector, and the corresponding respectively system of each element in the vector is in the probability of various different faults patterns, thereby realizes the Preliminary detection and the classification of fault.A major advantage of bayes method is that its variation tendency to gas in the oil is comparatively responsive; Thereby can find the variation that some are trickle in early days; As long as unusual increase has taken place in the content of gas in the oil; Bayesian algorithm can both be found this trend in time, no matter and how many reference values of its normal operation is.
Corresponding with above-mentioned a kind of power transformer fault monitoring method, the present invention also provides a kind of power transformer fault monitoring device, and is as shown in Figure 2, comprising:
The Characteristic Extraction module is used for polynary monitored parameters is carried out Characteristic Extraction and compression;
The function calculation module is used for the probability distribution function of calculated characteristics amount under transformer normal operation and fault mode;
The failure modes module is used for upgrading the posterior probability function according to the data in real time that newly monitors, and carries out failure modes according to posterior probability.
As an embodiment preferably; Device of the present invention can also comprise the cleaning module, is used for before carrying out Characteristic Extraction and compressing, original test data being cleared up; Filtering extracts the useful information directly related with transformer health status from the interference of external factor.
Preferably, said cleaning module can be come original test data is cleared up through the vectorial auto-regressive time series model VARX of supplementary variable;
Preferably, said failure modes module can utilize Bayes's control theory to carry out failure modes.
Other technical characterictic in the power transformer fault monitoring device of the present invention is identical with a kind of power transformer fault monitoring method of the present invention, does not repeat them here.
Can find out through above scheme; Power transformer fault monitoring method of the present invention and device; It at first carries out pre-service through statistical model to data, and then calculating transformer is in the probability of malfunction, realizes the classification and the monitoring of fault through posterior probability.Method of the present invention and device can utilize the transformer monitoring data to judge the health status of transformer; In time find latency fault and fault progression trend; Replace scheduled overhaul with repair based on condition of component, thereby reach the generation of minimizing accident, the purpose of saving maintenance cost.
Above-described embodiment of the present invention does not constitute the qualification to protection domain of the present invention.Any modification of within spirit of the present invention and principle, being done, be equal to replacement and improvement etc., all should be included within the claim protection domain of the present invention.
Claims (10)
1. a power transformer fault monitoring method is characterized in that, comprises the steps:
Polynary monitored parameters is carried out Characteristic Extraction and compression;
The probability distribution function of calculated characteristics amount under transformer normal operation and fault mode;
Upgrade the posterior probability function according to the data in real time that newly monitors, and carry out failure modes according to posterior probability.
2. power transformer fault monitoring method according to claim 1; It is characterized in that; Also comprise step said polynary monitored parameters is carried out before Characteristic Extraction and the compression: original test data is cleared up; Filtering extracts the useful information directly related with transformer health status from the interference of external factor.
3. power transformer fault monitoring method according to claim 2; It is characterized in that the said process that original test data is cleared up specifically comprises: the vectorial auto-regressive time series model VARX through supplementary variable comes original test data is cleared up; The normal structure of said VARX model is:
Wherein, X
tThe oil chromatography data of table t transformer monitoring constantly, X
T-iBe the oil chromatography data of t-i transformer monitoring constantly, ε
tBe t random disturbance constantly, d
T-iBe t-i external interference data constantly.
4. power transformer fault monitoring method according to claim 1; It is characterized in that the said process that polynary monitored parameters is carried out Characteristic Extraction and compression specifically comprises: come polynary monitored parameters is carried out Characteristic Extraction and compression through PLS PLS; The universal model of said PLS is:
X=TP
T+E
Y=TQ
T+F;
Wherein, X is the oil chromatography data matrix of transformer monitoring, and the behavior observation time is classified gas projects as; Y is the indicating fault variable, is 0 and 1 to the training data value; T is a weighting coefficient matrix; P and Q are the loading matrix; E and F are the error vector of multivariate normal distribution.
5. power transformer fault monitoring method according to claim 1; It is characterized in that; The process of the probability distribution function of said calculated characteristics amount under transformer normal operation and fault mode specifically comprises: output data Y is carried out histogram analysis; Fault is divided into overheating fault and discharge fault two big classifications; The basic distribution situation of Y value when judging all kinds of faults with normal operation uses normal distribution that these histograms are fitted, the distribution function of Y under the distribution function of Y, the discharge fault condition under the distribution function under the acquisition normal condition, the overheating fault condition.
6. power transformer fault monitoring method according to claim 5 is characterized in that, the process that data in real time that said basis newly monitors upgrades the posterior probability function, carry out failure modes according to posterior probability specifically comprises:
Use Monitoring Data Y to come update system state X, utilize Bayesian formula to realize:
Utilization comes computing system to be in the posterior probability P of malfunction by the end of all historical datas of present moment t=mh; Wherein, h is the SI, and m is by the end of t sampling total degree constantly; And come more new model that following formula is used in the judgement of system failure state according to the value that newly observes:
P
t=1-(1-P
Mh) e
-θ (t-mh), to the h of mh<t<(m+1);
On the basis of Bayes's posterior probability, calculate system according to the distribution function of Y under the distribution function of Y under the distribution function under the said normal condition, the overheating fault condition, the discharge fault condition and be in posterior probability overheated, discharge, carry out failure modes.
7. a power transformer fault monitoring device is characterized in that, comprising:
The Characteristic Extraction module is used for polynary monitored parameters is carried out Characteristic Extraction and compression;
The function calculation module is used for the probability distribution function of calculated characteristics amount under transformer normal operation and fault mode;
The failure modes module is used for upgrading the posterior probability function according to the data in real time that newly monitors, and carries out failure modes according to posterior probability.
8. power transformer fault monitoring device according to claim 7; It is characterized in that; Also comprise the cleaning module, be used for before carrying out Characteristic Extraction and compressing, original test data being cleared up; Filtering extracts the useful information directly related with transformer health status from the interference of external factor.
9. power transformer fault monitoring device according to claim 8 is characterized in that, said cleaning module comes original test data is cleared up through the vectorial auto-regressive time series model VARX of supplementary variable.
10. according to any described power transformer fault monitoring device of claim 7-9, it is characterized in that said failure modes module utilizes Bayes's control theory to carry out failure modes.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201110370683.6A CN102411106B (en) | 2011-11-18 | 2011-11-18 | Fault monitoring method and device for power transformer |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201110370683.6A CN102411106B (en) | 2011-11-18 | 2011-11-18 | Fault monitoring method and device for power transformer |
Publications (2)
Publication Number | Publication Date |
---|---|
CN102411106A true CN102411106A (en) | 2012-04-11 |
CN102411106B CN102411106B (en) | 2014-01-15 |
Family
ID=45913301
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201110370683.6A Active CN102411106B (en) | 2011-11-18 | 2011-11-18 | Fault monitoring method and device for power transformer |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN102411106B (en) |
Cited By (25)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102779230A (en) * | 2012-06-14 | 2012-11-14 | 华南理工大学 | State analysis and maintenance decision judging method of power transformer system |
CN102928720A (en) * | 2012-11-07 | 2013-02-13 | 广东电网公司 | Defect rate detecting method of oil immersed type main transformer |
CN103023719A (en) * | 2012-12-04 | 2013-04-03 | 宁夏隆基宁光仪表有限公司 | Specified transformer acquisition terminal failure diagnosis method based on bayesian network |
CN103197177A (en) * | 2013-03-20 | 2013-07-10 | 山东电力集团公司济宁供电公司 | Transformer fault diagnosis analysis method based on bayesian network |
CN103995775A (en) * | 2014-05-20 | 2014-08-20 | 浪潮电子信息产业股份有限公司 | Testing data generating method based on neural network |
CN104007343A (en) * | 2014-05-23 | 2014-08-27 | 清华大学 | Dynamic comprehensive transformer fault diagnosis method based on Bayesian network |
CN104076231A (en) * | 2014-07-16 | 2014-10-01 | 胡小青 | Electrical fault detecting method for power transmission transformer |
CN104316803A (en) * | 2014-11-04 | 2015-01-28 | 国家电网公司 | Power transformer state evaluation method and system based on electriferous detection |
CN104374842A (en) * | 2014-11-11 | 2015-02-25 | 深圳供电局有限公司 | Oil chromatography online monitoring data confidence coefficient analyzing method and system |
CN104655948A (en) * | 2013-11-21 | 2015-05-27 | 国家电网公司 | Novel multistage fault diagnosis method for power transformer |
CN105044499A (en) * | 2015-07-01 | 2015-11-11 | 国家电网公司 | Method for detecting transformer state of electric power system equipment |
CN105242129A (en) * | 2015-08-28 | 2016-01-13 | 广西电网有限责任公司电力科学研究院 | Fault probability determination method for transformer winding |
CN106292631A (en) * | 2016-08-25 | 2017-01-04 | 哈尔滨理工大学 | A kind of PWM rectifier fault diagnosis system based on neutral net |
CN107888397A (en) * | 2016-09-30 | 2018-04-06 | 华为技术有限公司 | The method and apparatus for determining fault type |
CN107944571A (en) * | 2017-11-09 | 2018-04-20 | 华北电力大学(保定) | A kind of power transformer remaining life Forecasting Methodology |
CN108427398A (en) * | 2018-03-06 | 2018-08-21 | 宁波大学 | A kind of dynamic process monitoring method based on distributing AR-PLS models |
CN108508319A (en) * | 2018-03-26 | 2018-09-07 | 中国石油大学(华东) | Transformer fault kind identification method based on linked character between fault characteristic gases |
CN109062177A (en) * | 2018-06-29 | 2018-12-21 | 无锡易通精密机械股份有限公司 | A kind of Trouble Diagnostic Method of Machinery Equipment neural network based and system |
CN109472369A (en) * | 2017-09-06 | 2019-03-15 | 云南电网有限责任公司保山供电局 | The monitoring method and device of power equipment |
TWI693415B (en) * | 2019-02-15 | 2020-05-11 | 南臺學校財團法人南臺科技大學 | Transformer diagnosis method, system, computer program product and computer readable recording medium |
CN111597655A (en) * | 2020-05-19 | 2020-08-28 | 西安航天动力技术研究所 | Product health judgment method based on fault occurrence probability |
CN111650451A (en) * | 2020-04-28 | 2020-09-11 | 中国南方电网有限责任公司超高压输电公司广州局 | Converter transformer fault reason identification method and system |
CN111914891A (en) * | 2020-06-23 | 2020-11-10 | 国网天津市电力公司电力科学研究院 | Fault data-based electric energy meter service life prediction method |
CN112201260A (en) * | 2020-09-07 | 2021-01-08 | 北京科技大学 | Transformer running state online detection method based on voiceprint recognition |
CN117057486A (en) * | 2023-10-11 | 2023-11-14 | 云南电投绿能科技有限公司 | Operation and maintenance cost prediction method, device and equipment for power system and storage medium |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20110010106A1 (en) * | 2008-04-11 | 2011-01-13 | Mitsubishi Electric Corporation | Apparatus state detector, method for detecting apparatus state, apparatus state detection server and apparatus state detection system; living persons' anomaly detector, living persons' anomaly detection system and method for detecting living persons' anomaly, and apparatus-state database maintenance server |
CN102221651A (en) * | 2011-03-11 | 2011-10-19 | 太原理工大学 | Fault on-line diagnosis and early warning method of flameproof dry-type transformer for mine |
-
2011
- 2011-11-18 CN CN201110370683.6A patent/CN102411106B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20110010106A1 (en) * | 2008-04-11 | 2011-01-13 | Mitsubishi Electric Corporation | Apparatus state detector, method for detecting apparatus state, apparatus state detection server and apparatus state detection system; living persons' anomaly detector, living persons' anomaly detection system and method for detecting living persons' anomaly, and apparatus-state database maintenance server |
CN101981601A (en) * | 2008-04-11 | 2011-02-23 | 三菱电机株式会社 | Device state detecting device, device state detecting method, device state detecting server, device state detecting system, liver abnormality detecting device, liver abnormality detecting system, liver abnormality detecting method, and device state d |
CN102221651A (en) * | 2011-03-11 | 2011-10-19 | 太原理工大学 | Fault on-line diagnosis and early warning method of flameproof dry-type transformer for mine |
Non-Patent Citations (1)
Title |
---|
吴立增等: "基于贝叶斯网络分类器的变压器综合故障诊断方法", 《电工技术学报》 * |
Cited By (38)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102779230B (en) * | 2012-06-14 | 2015-01-28 | 华南理工大学 | State analysis and maintenance decision judging method of power transformer system |
CN102779230A (en) * | 2012-06-14 | 2012-11-14 | 华南理工大学 | State analysis and maintenance decision judging method of power transformer system |
CN102928720A (en) * | 2012-11-07 | 2013-02-13 | 广东电网公司 | Defect rate detecting method of oil immersed type main transformer |
CN102928720B (en) * | 2012-11-07 | 2015-02-11 | 广东电网公司 | Defect rate detecting method of oil immersed type main transformer |
CN103023719A (en) * | 2012-12-04 | 2013-04-03 | 宁夏隆基宁光仪表有限公司 | Specified transformer acquisition terminal failure diagnosis method based on bayesian network |
CN103197177B (en) * | 2013-03-20 | 2015-09-23 | 山东电力集团公司济宁供电公司 | A kind of transformer fault diagnosis analytical approach based on Bayesian network |
CN103197177A (en) * | 2013-03-20 | 2013-07-10 | 山东电力集团公司济宁供电公司 | Transformer fault diagnosis analysis method based on bayesian network |
CN104655948A (en) * | 2013-11-21 | 2015-05-27 | 国家电网公司 | Novel multistage fault diagnosis method for power transformer |
CN103995775A (en) * | 2014-05-20 | 2014-08-20 | 浪潮电子信息产业股份有限公司 | Testing data generating method based on neural network |
CN104007343A (en) * | 2014-05-23 | 2014-08-27 | 清华大学 | Dynamic comprehensive transformer fault diagnosis method based on Bayesian network |
CN104076231A (en) * | 2014-07-16 | 2014-10-01 | 胡小青 | Electrical fault detecting method for power transmission transformer |
CN104316803A (en) * | 2014-11-04 | 2015-01-28 | 国家电网公司 | Power transformer state evaluation method and system based on electriferous detection |
CN104374842A (en) * | 2014-11-11 | 2015-02-25 | 深圳供电局有限公司 | Oil chromatography online monitoring data confidence coefficient analyzing method and system |
CN104374842B (en) * | 2014-11-11 | 2016-01-20 | 深圳供电局有限公司 | A kind of oil chromatography online monitoring data Confidence Analysis method and system |
CN105044499A (en) * | 2015-07-01 | 2015-11-11 | 国家电网公司 | Method for detecting transformer state of electric power system equipment |
CN105242129A (en) * | 2015-08-28 | 2016-01-13 | 广西电网有限责任公司电力科学研究院 | Fault probability determination method for transformer winding |
CN105242129B (en) * | 2015-08-28 | 2018-03-13 | 广西电网有限责任公司电力科学研究院 | A kind of transformer winding fault probability determination method |
CN106292631A (en) * | 2016-08-25 | 2017-01-04 | 哈尔滨理工大学 | A kind of PWM rectifier fault diagnosis system based on neutral net |
CN107888397A (en) * | 2016-09-30 | 2018-04-06 | 华为技术有限公司 | The method and apparatus for determining fault type |
CN107888397B (en) * | 2016-09-30 | 2020-12-25 | 华为技术有限公司 | Method and device for determining fault type |
US11140021B2 (en) | 2016-09-30 | 2021-10-05 | Huawei Technologies Co., Ltd. | Method and apparatus for determining fault type |
CN109472369A (en) * | 2017-09-06 | 2019-03-15 | 云南电网有限责任公司保山供电局 | The monitoring method and device of power equipment |
CN107944571A (en) * | 2017-11-09 | 2018-04-20 | 华北电力大学(保定) | A kind of power transformer remaining life Forecasting Methodology |
CN107944571B (en) * | 2017-11-09 | 2021-12-21 | 华北电力大学(保定) | Method for predicting residual service life of power transformer |
CN108427398A (en) * | 2018-03-06 | 2018-08-21 | 宁波大学 | A kind of dynamic process monitoring method based on distributing AR-PLS models |
CN108427398B (en) * | 2018-03-06 | 2020-06-16 | 宁波大学 | Dynamic process monitoring method based on distributed AR-PLS model |
CN108508319A (en) * | 2018-03-26 | 2018-09-07 | 中国石油大学(华东) | Transformer fault kind identification method based on linked character between fault characteristic gases |
CN109062177A (en) * | 2018-06-29 | 2018-12-21 | 无锡易通精密机械股份有限公司 | A kind of Trouble Diagnostic Method of Machinery Equipment neural network based and system |
TWI693415B (en) * | 2019-02-15 | 2020-05-11 | 南臺學校財團法人南臺科技大學 | Transformer diagnosis method, system, computer program product and computer readable recording medium |
CN111650451A (en) * | 2020-04-28 | 2020-09-11 | 中国南方电网有限责任公司超高压输电公司广州局 | Converter transformer fault reason identification method and system |
CN111650451B (en) * | 2020-04-28 | 2021-12-31 | 中国南方电网有限责任公司超高压输电公司广州局 | Converter transformer fault reason identification method and system |
CN111597655A (en) * | 2020-05-19 | 2020-08-28 | 西安航天动力技术研究所 | Product health judgment method based on fault occurrence probability |
CN111597655B (en) * | 2020-05-19 | 2023-04-21 | 西安航天动力技术研究所 | Product health judging method based on fault occurrence probability |
CN111914891A (en) * | 2020-06-23 | 2020-11-10 | 国网天津市电力公司电力科学研究院 | Fault data-based electric energy meter service life prediction method |
CN112201260B (en) * | 2020-09-07 | 2021-10-12 | 北京科技大学 | Transformer running state online detection method based on voiceprint recognition |
CN112201260A (en) * | 2020-09-07 | 2021-01-08 | 北京科技大学 | Transformer running state online detection method based on voiceprint recognition |
CN117057486A (en) * | 2023-10-11 | 2023-11-14 | 云南电投绿能科技有限公司 | Operation and maintenance cost prediction method, device and equipment for power system and storage medium |
CN117057486B (en) * | 2023-10-11 | 2023-12-22 | 云南电投绿能科技有限公司 | Operation and maintenance cost prediction method, device and equipment for power system and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN102411106B (en) | 2014-01-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN102411106B (en) | Fault monitoring method and device for power transformer | |
Zhou et al. | An opportunistic condition-based maintenance strategy for offshore wind farm based on predictive analytics | |
CN111596604B (en) | Intelligent fault diagnosis and self-healing control system and method for engineering equipment based on digital twinning | |
CN102779230B (en) | State analysis and maintenance decision judging method of power transformer system | |
CN100470416C (en) | Power plant thermal equipment intelligent state diagnosing and analyzing system | |
CN103711645B (en) | Based on the wind power generating set state evaluating method of modeling parameters signature analysis | |
CN102736546B (en) | State monitoring device of complex electromechanical system for flow industry and method | |
CN108564254A (en) | Controller switching equipment status visualization platform based on big data | |
CN109977624A (en) | Photovoltaic plant soft fault monitoring method based on deep neural network | |
CN110046182A (en) | A kind of huge hydroelectric power plant's intelligent alarm threshold setting method and system | |
CN104504607A (en) | Method for diagnosing photovoltaic power station faults on the basis of fuzzy clustering algorithm | |
CN105740975A (en) | Data association relationship-based equipment defect assessment and prediction method | |
CN104399682A (en) | Intelligent decision pre-warning system for sweeping of photovoltaic power station components | |
CN109492790A (en) | Wind turbines health control method based on neural network and data mining | |
CN107291830A (en) | A kind of creation method of equipment knowledge base | |
CN102261671A (en) | Boiler combustion multi-constraint and multi-object optimization expert system and optimization method thereof | |
CN103310296A (en) | Operation ticket security check method based on disturbance evaluation and trend analysis | |
EP2971768B1 (en) | Development of a superior model for controlling and/or supervising a compressor system | |
CN102592004B (en) | System and method for on-line analysis and diagnosis of whole-process energy-consuming conditions of integrated iron and steel works | |
CN104050377A (en) | Method for determining probability of time-varying equipment failures | |
CN102095953B (en) | A kind of performance of accumulator charger online test method | |
CN202091172U (en) | Device for monitoring state and analyzing reliability of gas compressor | |
KR20220089853A (en) | Method for Failure prediction and prognostics and health management of renewable energy generation facilities using machine learning technology | |
CN105741184A (en) | Transformer state evaluation method and apparatus | |
CN113807027B (en) | Wind turbine generator system health state evaluation model, method and system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant | ||
CP01 | Change in the name or title of a patent holder | ||
CP01 | Change in the name or title of a patent holder |
Address after: 510620, No. two, No. 2, Tianhe South Road, Guangzhou, Guangdong, Tianhe District Patentee after: Guangzhou Power Supply Bureau of Guangdong Power Grid Co.,Ltd. Address before: 510620, No. two, No. 2, Tianhe South Road, Guangzhou, Guangdong, Tianhe District Patentee before: Guangzhou Power Supply Bureau of Guangdong Power Grid Co.,Ltd. |