CN111044176A - Method for monitoring temperature abnormity of generator - Google Patents
Method for monitoring temperature abnormity of generator Download PDFInfo
- Publication number
- CN111044176A CN111044176A CN202010000525.0A CN202010000525A CN111044176A CN 111044176 A CN111044176 A CN 111044176A CN 202010000525 A CN202010000525 A CN 202010000525A CN 111044176 A CN111044176 A CN 111044176A
- Authority
- CN
- China
- Prior art keywords
- data
- abnormal
- generator
- temperature
- correlation
- 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
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01K—MEASURING TEMPERATURE; MEASURING QUANTITY OF HEAT; THERMALLY-SENSITIVE ELEMENTS NOT OTHERWISE PROVIDED FOR
- G01K13/00—Thermometers specially adapted for specific purposes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
Abstract
The application provides a monitoring method for abnormal temperature of a generator, which comprises the steps of analyzing a normal state and an abnormal state of historical data, exploring a correlation relation between data from the data perspective, establishing a corresponding judgment condition, judging whether a certain operation parameter is abnormal or not, and avoiding the current situation that a proper evaluation standard is difficult to select due to the complex operation data and the large relative dispersion degree of the data of a wind turbine; meanwhile, the method has small calculation difficulty through a judgment mode of the correlation matrix, is easy to realize, and solves the problems of high training difficulty and complex calculation of the existing model.
Description
Technical Field
The invention relates to a method for monitoring temperature abnormity of a generator, which is suitable for a wind generating set and belongs to the technical field of on-line monitoring methods of wind generating sets.
Background
In recent years, with the rapid development of wind power industry in China, the problem of faults of wind power generation sets gradually draws attention along with the continuous increase of the number of the wind power generation sets. The generator is one of the important components of the wind turbine, and the running state of the generator system directly influences the running performance and efficiency of the whole wind turbine.
The temperature parameter is one of the most commonly used process parameters in industrial production, and changes along with the changes of the environmental temperature and the output performance of the wind turbine generator, and if the generator has a fault heating condition, the related parameters are abnormal, so that monitoring is performed on the related temperature of the generator, and the early warning and diagnosis of the generator fault are particularly important. At present, the research aiming at the temperature signals of the generator mainly focuses on the aspects of component temperature prediction and fault diagnosis, and the basic idea is to analyze the operating temperature of the component in a normal state, and establish a temperature prediction and fault diagnosis model of the component by taking the fitted root mean square error or residual error as an evaluation index. However, due to the complex operation data of the wind turbine generator and the large relative dispersion degree of the data, a proper evaluation standard is difficult to select; and the operation parameters are numerous, model training needs to be carried out one by one according to the temperature parameters of the generator, the model training difficulty is high, and the calculation is complex.
Disclosure of Invention
The technical problem that this application will solve is: in the prior art, the temperature prediction and fault diagnosis model of the generator component is difficult, the calculation is complex, and the evaluation of the wind turbine generator operating data is difficult.
In order to solve the above problem, the technical solution of the present application is to provide a method for monitoring temperature abnormality of a generator, which is characterized by comprising the following steps:
acquiring historical data of generator temperature related parameters, integrating and cleaning the data, and deleting abnormal data and invalid data;
dividing the time sequence of the historical data into normal operation data and abnormal operation data according to whether the temperature of the generator fails, and marking the normal operation data and the abnormal operation data;
step three: dividing the time sequence of the historical data into different data sets hour by hour, and calculating a correlation coefficient matrix of the data sets hour by utilizing a correlation algorithm;
step four: analyzing different data sets comprising marked normal operation data and marked abnormal operation data, and establishing a judgment condition of the abnormal temperature of the generator according to the correlation level of the different data sets;
step five: calculating a correlation coefficient matrix of the data set once per hour, checking whether each parameter meets a condition, and if the condition is met, judging that no abnormity exists; if not, judging that the corresponding parameters are abnormal.
Preferably, the determination condition is that if the correlation between a certain parameter and more than 50% of the operation parameter data is less than 0.5, the parameter is considered to be abnormal; otherwise, the parameter is considered normal.
Preferably, in the second step, the normal operation data is marked as 1, and the abnormal operation data is marked as 0.
Preferably, the element of the ith row and the jth column of the correlation coefficient matrix is the correlation coefficient of the ith row and the jth column of the original data set matrix, and the correlation coefficient matrix
Wherein
cov(Xi,Xj)＝E((Xi-E(Xi))(Xj-E(Xj)))
Compared with the prior art, the beneficial effects of this application are:
the invention searches the correlation among data by analyzing the normal state and the abnormal state of historical data from the data perspective, establishes corresponding judgment conditions and judges whether a certain operation parameter is abnormal or not, thereby avoiding the current situation that the proper evaluation standard is difficult to select due to the complex operation data and the large relative dispersion degree of the data of the wind turbine; meanwhile, the method has small calculation difficulty through a judgment mode of the correlation matrix, is easy to realize, and solves the problems of high training difficulty and complex calculation of the existing model.
Drawings
Fig. 1 is a flow chart of steps of a method for monitoring temperature abnormality of a generator according to the present invention.
Detailed Description
In order to make the present application more comprehensible, preferred embodiments are described in detail below with reference to the accompanying drawings.
The invention relates to a method for monitoring temperature abnormity of a generator, which mainly comprises the following steps:
the method comprises the following steps: data integration and cleaning are carried out, collection and arrangement of historical data are completed, generator temperature related parameters are extracted, historical operating data of the fan are cleaned, and abnormal data and invalid data are deleted and recorded;
step two: and dividing the time sequence of the historical data according to whether the temperature of the generator fails, wherein the normal operation data is marked as 1, and the abnormal operation data is marked as 0. The correlation of completely normal operation data and the correlation of completely abnormal data can be accurately found in the correlation analysis process, and the judgment condition of the abnormality of the correlation can be conveniently compared, analyzed and summarized;
step three: dividing the time sequence of the historical data into different data sets hour by hour, and calculating a correlation coefficient matrix hour by utilizing a correlation algorithm;
the correlation coefficient matrix is formed by the correlation coefficients between the columns of the matrix. That is, the element in the ith row and the jth column of the correlation matrix is the correlation coefficient in the ith row and the jth column of the original matrix. Let the correlation matrix of a plurality of temperature measurement points be denoted as R, namely:
wherein
cov(Xi,Xj)＝E((Xi-E(Xi))(Xj-E(Xj)))
Step four: analyzing different data sets comprising a mark 0 and a mark 1, and establishing a judgment condition of the abnormal temperature of the generator according to the correlation level of the different data sets; the determination conditions were as follows: and if the correlation between a certain parameter and more than 50% of the operation parameters is less than 0.5, determining that the parameter is abnormal.
Step five: and calculating a correlation coefficient matrix of the data once per hour, checking whether each parameter meets the condition, if so, judging that no abnormality exists, and if not, judging that the corresponding parameter is abnormal.
Claims (4)
1. A method for monitoring temperature abnormity of a generator is characterized by comprising the following steps:
acquiring historical data of generator temperature related parameters, integrating and cleaning the data, and deleting abnormal data and invalid data;
dividing the time sequence of the historical data into normal operation data and abnormal operation data according to whether the temperature of the generator fails, and marking the normal operation data and the abnormal operation data;
step three: dividing the time sequence of the historical data into different data sets hour by hour, and calculating a correlation coefficient matrix of the data sets hour by utilizing a correlation algorithm;
step four: analyzing different data sets comprising marked normal operation data and marked abnormal operation data, and establishing a judgment condition of the abnormal temperature of the generator according to the correlation level of the different data sets;
step five: calculating a correlation coefficient matrix of the data set once per hour, checking whether each parameter meets a condition, and if the condition is met, judging that no abnormity exists; if not, judging that the corresponding parameters are abnormal.
2. A method of monitoring a temperature anomaly in an electrical generator as claimed in claim 1, characterized by: the judgment condition is that if the correlation between a certain parameter and more than 50% of the operation parameter data is less than 0.5, the parameter is considered to be abnormal; otherwise, the parameter is considered normal.
3. A method of monitoring a temperature anomaly in an electrical generator as claimed in claim 1, characterized by: and in the second step, the normal operation data is marked as 1, and the abnormal operation data is marked as 0.
4. A method of monitoring a temperature anomaly in an electrical generator as claimed in claim 1, characterized by: the element of the ith row and the jth column of the correlation coefficient matrix is the correlation coefficient of the ith row and the jth column of the original data set matrix, and the correlation coefficient matrix
Wherein
cov(Xi,Xj)＝E((Xi-E(Xi))(Xj-E(Xj))) 。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010000525.0A CN111044176A (en) | 2020-01-02 | 2020-01-02 | Method for monitoring temperature abnormity of generator |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010000525.0A CN111044176A (en) | 2020-01-02 | 2020-01-02 | Method for monitoring temperature abnormity of generator |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111044176A true CN111044176A (en) | 2020-04-21 |
Family
ID=70243442
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010000525.0A Pending CN111044176A (en) | 2020-01-02 | 2020-01-02 | Method for monitoring temperature abnormity of generator |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111044176A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112211794A (en) * | 2020-09-02 | 2021-01-12 | 五凌电力有限公司新能源分公司 | Cabin temperature abnormity early warning method, device, equipment and medium of wind turbine generator |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103306893A (en) * | 2012-03-09 | 2013-09-18 | 北京光耀能源技术股份有限公司 | Failure early warning and alarming method for wind-driven generator |
| JP2016224042A (en) * | 2015-05-27 | 2016-12-28 | 東海旅客鉄道株式会社 | Temperature anomaly detection system, and temperature anomaly detection method |
| CN106640548A (en) * | 2016-12-19 | 2017-05-10 | 北京金风科创风电设备有限公司 | State monitoring method and device for wind generating set |
| CN107423435A (en) * | 2017-08-04 | 2017-12-01 | 电子科技大学 | The multi-level method for detecting abnormality of multidimensional space-time data |
| CN108572640A (en) * | 2018-05-10 | 2018-09-25 | 北京中能博泰科技有限公司 | A kind of industrial system intelligent diagnosing method |
-
2020
- 2020-01-02 CN CN202010000525.0A patent/CN111044176A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103306893A (en) * | 2012-03-09 | 2013-09-18 | 北京光耀能源技术股份有限公司 | Failure early warning and alarming method for wind-driven generator |
| JP2016224042A (en) * | 2015-05-27 | 2016-12-28 | 東海旅客鉄道株式会社 | Temperature anomaly detection system, and temperature anomaly detection method |
| CN106640548A (en) * | 2016-12-19 | 2017-05-10 | 北京金风科创风电设备有限公司 | State monitoring method and device for wind generating set |
| CN107423435A (en) * | 2017-08-04 | 2017-12-01 | 电子科技大学 | The multi-level method for detecting abnormality of multidimensional space-time data |
| CN108572640A (en) * | 2018-05-10 | 2018-09-25 | 北京中能博泰科技有限公司 | A kind of industrial system intelligent diagnosing method |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112211794A (en) * | 2020-09-02 | 2021-01-12 | 五凌电力有限公司新能源分公司 | Cabin temperature abnormity early warning method, device, equipment and medium of wind turbine generator |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108375476B (en) | Hydroelectric generating set health assessment method | |
| CN112684379A (en) | Transformer fault diagnosis system and method based on digital twinning | |
| CN112766342A (en) | Abnormity detection method for electrical equipment | |
| CN114723285B (en) | Power grid equipment safety evaluation prediction method | |
| CN111669123B (en) | Method and device for fault diagnosis of photovoltaic string | |
| CN112861350B (en) | Temperature overheating defect early warning method for stator winding of water-cooled steam turbine generator | |
| CN108092623A (en) | A kind of photovoltaic array multisensor fault detecting and positioning method | |
| CN110245460A (en) | A kind of batch process fault monitoring method based on multistage OICA | |
| CN111044176A (en) | Method for monitoring temperature abnormity of generator | |
| CN116973703A (en) | Acoustic diagnosis method for discharge fault and abnormal operation state of dry type air-core reactor | |
| CN114239708B (en) | Combustion engine abnormity detection method based on quality control chart theory | |
| US11339763B2 (en) | Method for windmill farm monitoring | |
| CN108760813B (en) | Gas turbine blade health monitoring system and method based on temperature signals | |
| CN114936520A (en) | Steam turbine fault early warning analysis method based on improved MSET | |
| CN111352365B (en) | Dustproof ventilation type electric power and electrical equipment cabinet and control method | |
| CN114417704A (en) | Wind turbine generator health assessment method based on improved stack type self-coding | |
| CN111914490A (en) | Pump station unit state evaluation method based on deep convolution random forest self-coding | |
| CN111695634A (en) | Data abnormal mutation point detection algorithm based on limited accompanying censoring mechanism | |
| CN115566997B (en) | Photovoltaic module attenuation test system and method for air compression station | |
| CN116664018B (en) | Power plant equipment running state evaluation platform | |
| CN116720983A (en) | Power supply equipment abnormality detection method and system based on big data analysis | |
| CN117972419A (en) | Anomaly-transporter photovoltaic power generation abnormality detection method | |
| CN117874663A (en) | Wind driven generator abnormality diagnosis device and diagnosis method thereof | |
| CN118041233A (en) | Photovoltaic power station equipment fault detection method and system | |
| CN115985072A (en) | Wind driven generator cabin temperature monitoring and early warning method and system based on machine learning |
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 | ||
| CB02 | Change of applicant information |
Address after: 200233 No. 7, Lane 888, Tianlin Road, Minhang District, Shanghai Applicant after: Shanghai Energy Technology Development Co.,Ltd. Address before: 201100 No. 7, Lane 888, Tianlin Road, Xuhui District, Shanghai Applicant before: CPI ELECTRIC POWER ENGINEERING CO.,LTD. |
|
| CB02 | Change of applicant information | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200421 |
|
| RJ01 | Rejection of invention patent application after publication |