CN110618984B - Shutdown vibration data cleaning method - Google Patents
Shutdown vibration data cleaning method Download PDFInfo
- Publication number
- CN110618984B CN110618984B CN201910796296.5A CN201910796296A CN110618984B CN 110618984 B CN110618984 B CN 110618984B CN 201910796296 A CN201910796296 A CN 201910796296A CN 110618984 B CN110618984 B CN 110618984B
- Authority
- CN
- China
- Prior art keywords
- data
- vibration
- shutdown
- cleaning
- qtl
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
-
- 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
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Operations Research (AREA)
- Probability & Statistics with Applications (AREA)
- Algebra (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Software Systems (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Quality & Reliability (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The invention belongs to the field of data preprocessing of mechanical equipment and discloses a method for cleaning shutdown vibration data. Firstly, preparing vibration characteristic data needing cleaning and stopping, secondly, calculating the maximum clearance ratio of the vibration data, judging whether the maximum clearance ratio exceeds a set standard, and cleaning the vibration data meeting the conditions if the maximum clearance ratio exceeds the set standard; if not, the shutdown data cleaning operation is not carried out. The shutdown data cleaning method provided by the invention has the characteristics of automatically cleaning shutdown data without manual intervention, has very strong universality and can solve the problem of shutdown data cleaning of different vibration signal types and different devices. The invention provides robust and reliable preprocessing analysis for the large data analysis of the state monitoring of the mechanical equipment. By applying the method, the accurate cleaning of the vibration shutdown data of the mechanical equipment can be realized, and a solid foundation is provided for the subsequent utilization of the data.
Description
Technical Field
The invention belongs to the field of data preprocessing of mechanical equipment, and particularly relates to a shutdown vibration data cleaning method.
Background
In the field of monitoring the state of mechanical equipment, the preprocessing of the monitoring data of the running state of the equipment is very necessary. The cleaning in which the data collected in the shutdown state is the most fundamental preprocessing. Because the current equipment state monitoring mostly does not introduce the operating condition parameter of equipment, like equipment rotational speed, equipment motor current etc. consequently can't judge whether equipment is shut down according to operating condition parameter to the vibration data of cleaning equipment state monitoring. Under the condition of no equipment operation condition data, the current cleaning shutdown state vibration data is mainly used for judging whether shutdown is performed or not by comparing the equipment vibration size with a set shutdown threshold value, so that the vibration data is cleaned. The method needs to set a vibration shutdown threshold, and when the vibration is lower than the threshold, the vibration collected at the moment is regarded as the vibration in the shutdown state. The method has the disadvantage that it is difficult to set a universal and effective threshold value to deal with the problem of cleaning the shutdown data of different types of equipment and even different operation environments of the same type of equipment. Meanwhile, the threshold value can be accurately set by a professional with certain equipment operation maintenance and vibration knowledge. Therefore, shutdown vibration data cleaning according to the vibration magnitude cannot be popularized and applied, and inaccurate threshold values can cause mistaken cleaning and missed cleaning of shutdown data.
Disclosure of Invention
The invention aims to provide a shutdown vibration data cleaning method, which is used for solving the problems of mistaken cleaning and missed cleaning caused by cleaning shutdown vibration data based on the magnitude of absolute magnitude of vibration in the prior art and the problem that the judgment threshold of the method cannot be universal and effective.
In order to realize the task, the invention adopts the following technical scheme:
a shutdown vibration data cleaning method comprises the following steps:
step 1: acquiring vibration data through a vibration sensor, selecting vibration data to be cleaned, and extracting a vibration characteristic value from the vibration data to be cleaned to obtain a vibration characteristic sequence V;
and 2, step: calculating a percentile value sequence qtl according to the vibration characteristic sequence V obtained in the step 1, then carrying out first-order difference on qtl to obtain a difference sequence H, and calculating the maximum gap ratio judgeratio of the vibration data to be cleaned according to H and qtl;
step 2.1: calculating a percentile value sequence qtl of the vibration characteristic sequence V by using a formula I;
qtl i = percentile (V, i) formula I
Where percentile represents the percentile value of the compute array, qtl = { qtl = i }，qtl i A value representing the ith percentile of the vibration signature sequence V, i =1,2,3.. 100;
step 2.2: carrying out first order difference on the percentile value sequence qtl obtained in the step 2.1 to obtain a difference sequence H, H = { H = m 99, acquiring a maximum value maxh of the differential sequence and a subscript maxm corresponding to the maximum value, wherein the maxm belongs to m;
step 2.3: calculating the maximum gap ratio judgeratio of the vibration data to be cleaned by using a formula II;
wherein Mean represents the calculated array Mean, qtl [ 1;
and 3, step 3: judging whether the vibration data to be cleaned contains shutdown data or not, if judgeratio is less than or equal to R, judging that the vibration data to be cleaned does not contain the shutdown data, not cleaning the data, wherein R represents the ratio of the running vibration to the shutdown vibration of the equipment and R is more than or equal to 3; if Judgeratio > R, the vibration data to be cleaned comprises shutdown data, and step 4 is executed;
and 4, step 4: making vibration characteristic sequence V smaller than qtl maxm+1 Judging the vibration characteristic value as stop data and deleting the stop data, and keeping the value more than or equal to qtl in the vibration characteristic sequence V maxm+1 And finishing the shutdown data cleaning by using the vibration characteristic value.
Further, the vibration data in step 1 includes displacement, speed and acceleration; if the vibration data is displacement, the vibration characteristic value is a displacement peak value; if the vibration data is speed, the vibration characteristic value is a speed effective value; if the vibration data is acceleration, the vibration characteristic value is an acceleration peak value.
Compared with the prior art, the invention has the following technical characteristics:
(1) The invention provides a shutdown vibration data cleaning method which has the characteristics of stability and reliability and can be suitable for shutdown vibration cleaning treatment of different types of equipment and different equipment operating condition environments. After the equipment vibration data of a period of time is selected, whether shutdown data exists is detected by calculating statistical indexes of the data.
(2) The method can calculate the distribution characteristic 'maximum gap ratio' of the data by utilizing the distribution statistical characteristics of the selected section of the historical operating state parameters of the equipment, designs the rules and the method for automatically cleaning the shutdown data based on the index, and finally realizes the reliable automatic cleaning of the shutdown data of the equipment.
Drawings
FIG. 1 is an overall flow diagram of shutdown data cleansing;
FIG. 2 illustrates a sequence of pump acceleration vibration signatures in an embodiment;
a percentile sequence corresponding to a pump vibration characteristic sequence in the embodiment of fig. 3;
the difference sequence of a certain pump percentage sequence pair in the embodiment of fig. 4;
the shutdown data cleaning result of a certain pump vibration characteristic sequence in the embodiment of FIG. 5;
FIG. 6 shows the result of cleaning the shutdown data for a certain pump oscillation speed;
FIG. 7 shows the result of cleaning the shutdown data of a certain fan vibration acceleration.
Detailed Description
In the present invention, the mechanical equipment required to detect the shutdown data includes engines, large prime movers, turbine generators, and rotating machinery, etc., where rotating machinery includes steam turbines, gas turbines, centrifugal and axial compressors, fans, pumps, water turbines, generators, aircraft engines, etc.
Example 1
The embodiment discloses a shutdown vibration data cleaning method, which comprises the following steps:
step 1: acquiring vibration data through a vibration sensor, selecting vibration data to be cleaned, extracting a vibration characteristic value from the vibration data to be cleaned to obtain a vibration characteristic sequence V, wherein the selected vibration data to be cleaned needs to contain data corresponding to equipment running, and the vibration data acquired when the equipment is in a shutdown state may be selected in the selection process;
and 2, step: calculating a percentile value sequence qtl according to the vibration characteristic sequence V obtained in the step 1, then carrying out first-order difference on qtl to obtain a difference sequence H, and calculating the maximum gap ratio judgeratio of the vibration data to be cleaned according to H and qtl;
step 2.1: calculating a percentile value sequence qtl of the vibration characteristic sequence V by using a formula I;
qtl i = percentile (V, i) formula I
Wherein, the percentile tableIndicating the percentile value of the calculated array, qtl = { qtl = i }，qtl i A value representing the ith percentile of the vibration signature sequence V, i =1,2,3.. 100;
step 2.2: performing first-order difference on the percentile value sequence qtl obtained in the step 2.1 to obtain a difference sequence H, wherein H = { H = m 99, acquiring a maximum value maxh of the differential sequence and a subscript maxm corresponding to the maximum value, wherein the maxm belongs to m;
step 2.3: calculating the maximum gap ratio judgeratio of the vibration data to be cleaned by using a formula II;
wherein Mean represents the calculated array Mean, qtl [ 1;
the maximum gap ratio judgeratio represents that the ratio of the maximum interval quantity to the data mean value before the interval in a section of vibration data after numerical values are sorted from small to large represents the degree of sudden change in the vibration data, if shutdown data exists, the data has obvious sudden change, the corresponding maximum gap ratio is very large, and the maximum gap ratio corresponding to the sudden change caused by the non-shutdown data is small;
and step 3: judging whether the vibration data to be cleaned contains shutdown data or not, if judgeratio is less than or equal to R, judging that the vibration data to be cleaned does not contain the shutdown data, and not cleaning the data; if judgeratio is greater than R, the vibration data to be cleaned comprises shutdown data, and step 4 is executed, wherein R represents the ratio of the operation vibration of the equipment to the shutdown vibration, R is greater than or equal to 3, the larger R is, the larger the difference between the operation vibration of the equipment and the shutdown vibration is, and the smaller R is, the smaller the difference between the operation vibration of the equipment and the shutdown vibration is;
and 4, step 4: making the vibration characteristic sequence V smaller than qtl maxm+1 Judging the vibration characteristic value as stop data and deleting the stop data, and keeping the value more than or equal to qtl in the vibration characteristic sequence V maxm+1 And finishing the shutdown data cleaning by using the vibration characteristic value.
The method uses a section of vibration data including the equipment running state, detects whether the shutdown data exists or not by calculating the statistical index of the vibration data, and further realizes the automatic cleaning of the equipment shutdown data. Compared with the traditional mode of cleaning shutdown data by observing the vibration magnitude of equipment and setting a fixed vibration threshold value, the shutdown data cleaning method provided by the invention has the characteristics of automatically cleaning the shutdown data without manual intervention, has very strong universality, calculates the maximum gap ratio by using a mathematical statistics method based on the numerical difference between the shutdown data and normal operation data, further quantitatively evaluates the mutation degree in the data, and can solve the problem of cleaning the shutdown data of different vibration signal types and different equipment.
The invention provides robust and reliable preprocessing analysis for the condition monitoring big data analysis of the mechanical equipment. By applying the invention, the accurate cleaning of the vibration shutdown data of the mechanical equipment can be realized, and a solid foundation is provided for the subsequent utilization of the data.
Further, a vibration sensor is arranged at a key part of the equipment, so that the vibration quantity of the equipment in the operation process is collected, vibration data needing to be cleaned are vibration characteristic values obtained by extracting vibration waveform data obtained by original collection, and the vibration data in the step 1 comprise displacement, speed and acceleration; if the vibration data is displacement, the vibration characteristic value is a displacement peak value; if the vibration data is speed, the vibration characteristic value is a speed effective value; if the vibration data is acceleration, the vibration characteristic value is an acceleration peak value.
Example 2
In this embodiment, a method for cleaning shutdown vibration data is disclosed, in which for a horizontal position of a non-driving end of a pump motor, vibration data is collected, and on the basis of embodiment 1, the following technical features are disclosed:
step 1: collecting vibration acceleration data through a vibration sensor, selecting vibration data to be cleaned, and extracting a vibration characteristic value from the vibration data to be cleaned to obtain a vibration acceleration characteristic sequence V = [43,41.3,41.2,43.7, ·,2.2,2.1]; the time series signature sequence contains 252 data points, and the time series trend is drawn as shown in fig. 2 below;
step 2: calculating a percentile sequence of values qtl = [1.4, 1.5,..,. 57.315,77.8] according to the vibration acceleration characteristic sequence V obtained in the step 1, wherein the sequence has 100 data points, drawing a percentile sequence diagram as shown in a following figure 3, and then carrying out first-order difference on qtl to obtain a difference sequence H = [0, 0.1,..,. 5.379,20.485], wherein 99 data points are obtained, drawing a difference sequence diagram as shown in a following figure 4, wherein the maximum difference value is 25.02 and the corresponding index number is 52; calculating the maximum gap ratio judgeratio =13.5319 of the vibration data to be cleaned according to H and qtl;
and step 3: the maximum gap ratio is greater than 3, so that it is judged that there is shutdown data in the data,
and 4, step 4: will be lower than the 53 th (52 + 1) percentile value: all data points of 28.02 are judged as shutdown data and cleaned, and the shutdown data cleaning is completed as shown in fig. 5.
As shown in fig. 1, the method is a flow chart of a shutdown vibration data cleaning method, and the method firstly prepares vibration characteristic data needing cleaning and shutdown, secondly calculates the maximum clearance ratio of the vibration data, judges whether the maximum clearance ratio exceeds a set standard, and cleans the vibration data meeting conditions if the maximum clearance ratio exceeds the set standard; if not, the shutdown data cleaning operation is not carried out.
Fig. 6 shows the result of cleaning the shutdown data for a certain pump oscillation speed using the present invention. In the figure, the vibration speed after 9, 11 days is low, corresponding to the shutdown state of the equipment, and cleaning is needed. If the method is based on the traditional cleaning method, vibration data lower than 1mm/s can be set after the data are observed, and the method is judged to be stopped, but the cleaning threshold value is determined through the observed data, an automatic cleaning process cannot be realized, and the obtained cleaning threshold value can only be suitable for stopping the vibration data of the equipment, and the method has no universality. By applying the cleaning method, the cleaning shutdown data completely conforms to the actual shutdown state of the equipment, the whole cleaning process is completely automatic, and the cleaning result is accurate.
FIG. 7 shows the result of cleaning the shutdown data of a certain fan vibration acceleration by using the present invention. In the figure, the vibration acceleration is low from 12 months 22 to 12 months 27, which corresponds to the apparatus stopped state and requires cleaning. If the method is based on the traditional cleaning method, vibration data lower than 4m/s ^2 can be set after data observation to judge that the machine is stopped, but the cleaning threshold is determined through the observation data, an automatic cleaning process cannot be realized, and the obtained cleaning threshold has no universality. The figure shows that the cleaning method of the invention has the cleaning shutdown data completely consistent with the actual shutdown state of the equipment, the whole cleaning process is completely automatic, and the cleaning result is accurate.
Claims (2)
1. A shutdown vibration data cleaning method is characterized by comprising the following steps:
step 1: acquiring vibration data through a vibration sensor, selecting vibration data to be cleaned, and extracting a vibration characteristic value from the vibration data to be cleaned to obtain a vibration characteristic sequence V;
step 2: calculating a percentile value sequence qtl according to the vibration characteristic sequence V obtained in the step 1, then carrying out first-order difference on qtl to obtain a difference sequence H, and calculating the maximum gap ratio judgeratio of the vibration data to be cleaned according to H and qtl;
step 2.1: calculating a percentile value sequence qtl of the vibration characteristic sequence V by using a formula I;
qtl i = percentile (V, i) formula I
Where percentile denotes the percentile value of the compute array, qtl = { qtl = i }，qtl i A value representing the ith percentile of the vibration signature sequence V, i =1,2,3.. 100;
step 2.2: carrying out first order difference on the percentile value sequence qtl obtained in the step 2.1 to obtain a difference sequence H, H = { H = m 99, acquiring a maximum value max h of the difference sequence and a subscript max m corresponding to the maximum value, wherein the max m belongs to m;
step 2.3: calculating the maximum gap ratio judgeratio of the vibration data to be cleaned by using a formula II;
wherein Mean represents the calculated array Mean, qtl [ 1;
and 3, step 3: judging whether the vibration data to be cleaned contains shutdown data or not, if judgeratio is less than or equal to R, judging that the vibration data to be cleaned does not contain the shutdown data, not cleaning the data, wherein R represents the ratio of the running vibration to the shutdown vibration of the equipment and R is more than or equal to 3; if Judgeratio > R, the vibration data to be cleaned comprises shutdown data, and step 4 is executed;
and 4, step 4: making the vibration characteristic sequence V smaller than qtl maxm+1 Judging the vibration characteristic value as stop data and deleting the stop data, and keeping the vibration characteristic value more than or equal to qtl in the vibration characteristic sequence V maxm+1 And finishing the shutdown data cleaning by using the vibration characteristic value.
2. The shutdown vibration data cleaning method of claim 1, wherein the vibration data in step 1 includes displacement, velocity and acceleration; if the vibration data is displacement, the vibration characteristic value is a displacement peak value; if the vibration data is speed, the vibration characteristic value is a speed effective value; and if the vibration data is the acceleration, the vibration characteristic value is the acceleration peak value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910796296.5A CN110618984B (en) | 2019-08-27 | 2019-08-27 | Shutdown vibration data cleaning method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910796296.5A CN110618984B (en) | 2019-08-27 | 2019-08-27 | Shutdown vibration data cleaning method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110618984A CN110618984A (en) | 2019-12-27 |
| CN110618984B true CN110618984B (en) | 2023-02-03 |
Family
ID=68922082
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910796296.5A Active CN110618984B (en) | 2019-08-27 | 2019-08-27 | Shutdown vibration data cleaning method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110618984B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112525337B (en) * | 2020-11-18 | 2023-06-02 | 西安因联信息科技有限公司 | Pretreatment method for vibration monitoring data of mechanical press |
| CN112525336B (en) * | 2020-11-18 | 2023-06-27 | 西安因联信息科技有限公司 | Automatic detection method for continuous vibration growth of mechanical equipment |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102778358A (en) * | 2012-06-04 | 2012-11-14 | 上海东锐风电技术有限公司 | Failure prediction model establishing method and system as well as fan monitoring pre-warning system and method |
| CN105628421A (en) * | 2015-12-25 | 2016-06-01 | 南京南瑞集团公司 | Hydroelectric generating set vibration limit monitoring and early warning method according to working conditions |
| CN106677996A (en) * | 2016-12-29 | 2017-05-17 | 科诺伟业风能设备（北京）有限公司 | Method for detecting vibration anomaly of tower drum of wind generating set |
| CN107146004A (en) * | 2017-04-20 | 2017-09-08 | 浙江大学 | A kind of slag milling system health status identifying system and method based on data mining |
| CN108320171A (en) * | 2017-01-17 | 2018-07-24 | 北京京东尚科信息技术有限公司 | Hot item prediction technique, system and device |
| CN110046151A (en) * | 2019-03-05 | 2019-07-23 | 努比亚技术有限公司 | A kind of data cleaning method, server and computer readable storage medium |
-
2019
- 2019-08-27 CN CN201910796296.5A patent/CN110618984B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102778358A (en) * | 2012-06-04 | 2012-11-14 | 上海东锐风电技术有限公司 | Failure prediction model establishing method and system as well as fan monitoring pre-warning system and method |
| CN105628421A (en) * | 2015-12-25 | 2016-06-01 | 南京南瑞集团公司 | Hydroelectric generating set vibration limit monitoring and early warning method according to working conditions |
| CN106677996A (en) * | 2016-12-29 | 2017-05-17 | 科诺伟业风能设备（北京）有限公司 | Method for detecting vibration anomaly of tower drum of wind generating set |
| CN108320171A (en) * | 2017-01-17 | 2018-07-24 | 北京京东尚科信息技术有限公司 | Hot item prediction technique, system and device |
| CN107146004A (en) * | 2017-04-20 | 2017-09-08 | 浙江大学 | A kind of slag milling system health status identifying system and method based on data mining |
| CN110046151A (en) * | 2019-03-05 | 2019-07-23 | 努比亚技术有限公司 | A kind of data cleaning method, server and computer readable storage medium |
Non-Patent Citations (2)
| Title |
|---|
| FDTD Calculations of the Diffraction Coefficient of Vibrating Wedges;Monica Madrid，等;《IEEE Antennas and Wireless Propagation Letters》;20110303;第10卷;第163-166页 * |
| 道路工程智能压实数据异常值识别处理方法研究;谢扬;《市政技术》;20180531;第36卷(第5期);第17-19页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110618984A (en) | 2019-12-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109488630B (en) | Centrifugal fan rotor misalignment fault diagnosis method based on harmonic relative index | |
| CN110618984B (en) | Shutdown vibration data cleaning method | |
| CN101603854A (en) | The rotating machinery non-stationery vibration signal instantaneous frequency estimation algorithm in start and stop period | |
| CN110905732B (en) | Method and system for identifying unbalance of wind wheel of wind turbine generator and storage medium | |
| CN110067708B (en) | Method for identifying yaw wind disharmony by using power curve | |
| CN112302966B (en) | Method and system for judging running state of centrifugal pump | |
| CN102966526B (en) | Based on the compressor low frequency flow induced vibrations class method for diagnosing faults that axial vibration is analyzed | |
| CN112329357B (en) | Simple diagnosis method and system for vibration fault of clean water centrifugal pump | |
| CN113176081B (en) | Historical data-based turbine blade wear monitoring method | |
| CN111120388A (en) | Fan state combined monitoring method and system | |
| CN112418306A (en) | Gas turbine compressor fault early warning method based on LSTM-SVM | |
| CN102095491A (en) | Method for analyzing low-frequency vibration mutability of steam turboset in real time | |
| CN108871827B (en) | Method for rapidly diagnosing rotary machine resonance based on cross statistical analysis | |
| CN108760268B (en) | Step fault diagnosis method for vertical mill operation data based on information entropy | |
| CN111307461A (en) | Rolling bearing fault detection method based on characteristic vector baseline method | |
| CN112525336B (en) | Automatic detection method for continuous vibration growth of mechanical equipment | |
| CN114607571A (en) | Offshore wind power gear box fault identification method and system based on lubricating system monitoring | |
| CN114412447A (en) | Fault detection method and device for screw pump well | |
| CN114295367A (en) | Wind turbine generator gearbox working condition online monitoring method | |
| CN113848347A (en) | Health state detection method for wind meter of wind driven generator | |
| CN111059004A (en) | Automatic state monitoring method and system suitable for fan series | |
| CN114033736B (en) | Fan fault monitoring system based on air pressure pulsation signal | |
| KR101472768B1 (en) | Method for checking of facility status with the number of vibrations of rotary machine | |
| CN102879085A (en) | Real-time low-frequency vibration unstable state early warning method for steam turbine generator unit | |
| Zhao et al. | Health indicator selection and health assessment of rolling element bearing |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |