CN115060491A - Fan bearing operation health degree assessment method and system based on multi-source data - Google Patents
Fan bearing operation health degree assessment method and system based on multi-source data Download PDFInfo
- Publication number
- CN115060491A CN115060491A CN202210720237.1A CN202210720237A CN115060491A CN 115060491 A CN115060491 A CN 115060491A CN 202210720237 A CN202210720237 A CN 202210720237A CN 115060491 A CN115060491 A CN 115060491A
- Authority
- CN
- China
- Prior art keywords
- monitoring data
- main bearing
- data
- fan
- health
- 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
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M13/00—Testing of machine parts
- G01M13/04—Bearings
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M13/00—Testing of machine parts
- G01M13/04—Bearings
- G01M13/045—Acoustic or vibration analysis
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/12—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing
Abstract
The invention discloses a fan bearing operation health degree assessment method and system based on multi-source data, and belongs to the technical field of bearing operation condition assessment. Firstly, acquiring information of a plurality of monitoring data sources of the fan main bearing, then carrying out noise reduction and feature extraction on signals of the acquired data sources, inputting the processed signal features into a fan main bearing health degree evaluation model, outputting fan main bearing comprehensive health indexes, finally comparing the obtained fan main bearing comprehensive health indexes with a calibrated threshold interval, determining the threshold interval where the fan main bearing comprehensive health indexes are located, completing health degree evaluation, and matching operation and maintenance strategies of different degrees according to health degree evaluation results. The invention can comprehensively and comprehensively evaluate the running health state of the main bearing of the fan, carry out preventive monitoring and reduce the shutdown maintenance cost and the power generation loss caused by failure.
Description
Technical Field
The invention belongs to the technical field of bearing running state assessment and maintenance, and particularly relates to a fan bearing running health assessment method and system based on multi-source data.
Background
The main bearing is one of important parts of the wind turbine, the operating state of the main bearing directly determines the service life and the operating reliability of the wind turbine, the health condition of the main bearing is very important for the health of the whole wind turbine, the impending faults can be identified and corrected through proper monitoring, if perfect monitoring is not available, and proper corrective measures cannot be taken when needed, the failure of the main bearing can cause the shutdown of the wind turbine and the loss of the power generation time.
The current mainstream fan main bearing state monitoring mainly takes vibration, temperature and other information of a bearing as main information, sets a corresponding alarm value according to the initial running state of the fan, and takes corresponding improvement measures when the monitoring state of the bearing is degraded to the alarm value. When parameters such as vibration, temperature and the like give an alarm, the bearing may have irreversible damage, and even if improvement measures are carried out, the damage cannot be prevented from further expanding, and finally the bearing fails.
The patent document 'rolling bearing health state online evaluation method and system' provides a ball bearing health state online evaluation method and system, mainly aims at processing and analyzing vibration signals to complete bearing health state evaluation including fault detection and fault diagnosis, and whether data sources or vibration data, and the evaluation method is mainly a K nearest neighbor method. The data source on which the evaluation of the method is based is only a single type of vibration signal, the bearing health state information cannot be comprehensively and intuitively reflected, and in addition, the K-nearest neighbor method is mature in classification scene use, but the calculated amount is large and further subdivision is not easy to realize in classification.
Disclosure of Invention
In order to solve the defects in the prior art, the invention aims to provide a fan bearing operation health degree evaluation method and system based on multi-source data, which can comprehensively and comprehensively evaluate the operation health state of a fan main bearing, perform preventive monitoring and reduce shutdown maintenance cost and power generation loss caused by failure.
The invention is realized by the following technical scheme:
a fan bearing operation health degree assessment method based on multi-source data comprises the following steps:
s1: collecting information of a plurality of monitoring data sources of a main bearing of a fan;
s2: carrying out noise reduction and feature extraction on the signals of the data sources acquired in the step S1;
s3: inputting the signal characteristics processed by the S2 into a fan main bearing health degree evaluation model, and outputting a fan main bearing comprehensive health index;
s4: and comparing the comprehensive health index of the fan main bearing obtained in the step S3 with a calibrated threshold interval, determining the threshold interval where the comprehensive health index of the fan main bearing is located, finishing health degree evaluation, and adopting operation and maintenance strategies of different degrees according to health degree evaluation results.
Preferably, in S1, the monitoring data sources include lubricating grease monitoring data, white corrosion crack risk monitoring data, pre-tightening force monitoring data, embedded temperature monitoring data and vibration monitoring data.
Further preferably, the lubricating grease monitoring data includes water content and temperature of grease; the white corrosion crack monitoring data comprise humidity and temperature in the operating environment of the main bearing, shaft voltage and partial discharge; the pretightening force monitoring data comprises inward pretightening force of the side surfaces of the inner ring and the outer ring of the bearing; the embedded temperature monitoring data comprises the surface temperature of the side surface of the inner ring of the main bearing; the vibration monitoring data includes vibration amplitude frequencies deployed at a plurality of detection locations.
Further preferably, in S2, data cleaning is performed on the signals of the collected data sources, and when the data collected at adjacent times have large fluctuation, relevant data are removed; when in noise reduction, the vibration monitoring data is subjected to noise reduction by adopting a variational modal decomposition algorithm, and median filtering noise reduction is performed on the lubricating grease monitoring data, the white corrosion crack risk monitoring data, the pretightening force monitoring data and the embedded temperature monitoring data; and extracting corresponding order spectrum characteristics from the vibration monitoring data during characteristic extraction, and extracting noise-reduced data from the lubricating grease monitoring data, the white corrosion crack risk monitoring data, the pretightening force monitoring data and the embedded temperature monitoring data.
Further preferably, all monitoring data are acquired at the same acquisition clock.
Preferably, in S3, the health evaluation model of the main bearing of the wind turbine is established based on a back propagation neural network algorithm.
Preferably, the training method of the health evaluation model of the main bearing of the wind turbine in S3 is as follows: the method comprises the steps of collecting multiple groups of data under different conditions of normal operation of a fan main bearing, poor grease lubrication, white corrosion crack generation and bearing roller abrasion respectively, extracting corresponding data signal characteristics as input vectors according to different rotating speeds, marking the output operation health degree according to experience, inputting the collected data characteristics into a fan main bearing health degree evaluation model, setting hidden layers to be 3 and total layers to be 5 according to the number of input parameters, and adjusting the weight of each layer through a back propagation algorithm to obtain a trained fan main bearing health degree evaluation model.
Preferably, in S4, the threshold interval is divided into a good interval, a medium interval and a poor interval, where the operation and maintenance policy taken in the good interval is only marked, the operation and maintenance policy taken in the good interval is continued observation, the operation and maintenance policy taken in the medium interval is on-site confirmation, and the operation and maintenance policy taken in the poor interval is shutdown inspection.
Preferably, after S4, the method further comprises: and (4) carrying out posterior analysis on the health degree evaluation result of the S4, and carrying out correction optimization on the health degree evaluation model of the fan main bearing in the S3 as a history record after secondary confirmation and annotation.
The invention discloses a fan bearing operation health degree evaluation system based on multi-source data, which comprises the following steps:
the monitoring data source acquisition module is used for acquiring information of a plurality of monitoring data sources of the fan main bearing;
the monitoring data source signal processing module is used for carrying out noise reduction and feature extraction on the acquired signals of each data source;
the fan main bearing comprehensive health index output module inputs the processed signal characteristics into the fan main bearing health degree evaluation model and outputs fan main bearing comprehensive health indexes;
and the health degree evaluation and operation and maintenance strategy matching module is used for comparing the obtained comprehensive health index of the fan main bearing with a calibrated threshold interval, determining the threshold interval where the comprehensive health index of the fan main bearing is located, finishing health degree evaluation, and matching operation and maintenance strategies of different degrees according to the health degree evaluation result.
Compared with the prior art, the invention has the following beneficial technical effects:
the invention discloses a fan bearing operation health degree assessment method based on multi-source data, which comprises the steps of firstly acquiring information of a plurality of monitoring data sources of a fan main bearing, then carrying out noise reduction and feature extraction on signals of the acquired data sources, inputting processed signal features into a fan main bearing health degree assessment model, outputting fan main bearing comprehensive health indexes, finally comparing the obtained fan main bearing comprehensive health indexes with a calibrated threshold interval, determining the threshold interval where the fan main bearing comprehensive health indexes are located, completing health degree assessment, and matching operation and maintenance strategies of different degrees according to health degree assessment results. The data sources acquired by the method are richer, and the acquired multidimensional data can represent the running health state of the main bearing of the fan more comprehensively from multiple aspects, so that the health degree evaluation method is more comprehensive and more comprehensive. Meanwhile, preventive monitoring can be carried out, data sources such as lubricating grease monitoring data and the like can capture the bad operation trend of the main bearing before failure occurs in the bearing failure occurrence process, errors can be corrected in time, and the shutdown maintenance cost and the power generation loss caused by failure are reduced.
Furthermore, all monitoring data are collected under the same collecting clock, and the synchronism of data collection is ensured.
The multi-source data-based fan bearing operation health degree evaluation system disclosed by the invention is simple in system construction and good in compatibility with the existing software and hardware.
Drawings
FIG. 1 is a flow chart of a method for evaluating the running health of a main bearing of a fan based on multi-source data according to the present invention;
FIG. 2 is a schematic diagram of a main bearing operation health degree evaluation model framework in the embodiment.
Detailed Description
The present invention will now be described in further detail with reference to the following figures and specific examples, which are intended to be illustrative, but not limiting, of the invention.
Referring to fig. 1, the method for evaluating the operation health of the fan bearing based on the multi-source data comprises the following steps:
s1: collecting information of a plurality of monitoring data sources of a main bearing of a fan; the monitoring data source comprises lubricating grease monitoring data, white corrosion crack risk monitoring data, pretightening force monitoring data, embedded temperature monitoring data and vibration monitoring data. The lubricating grease monitoring data comprises the water content and the temperature of the grease; the white corrosion crack monitoring data comprise humidity and temperature in the operating environment of the main bearing, shaft voltage and partial discharge; the pretightening force monitoring data comprises inward pretightening force of the side surfaces of the inner ring and the outer ring of the bearing; the embedded temperature monitoring data comprises the surface temperature of the side surface of the inner ring of the main bearing; the vibration monitoring data includes vibration amplitude frequencies deployed at a plurality of detection locations. All monitoring data are collected under the same collecting clock
S2: carrying out noise reduction and feature extraction on the signals of the data sources acquired in the step S1; firstly, data cleaning is carried out on collected signals of each data source, and relevant data are removed when the data collected at adjacent moments have large fluctuation; when in noise reduction, the vibration monitoring data is subjected to noise reduction by adopting a variational modal decomposition algorithm, and median filtering noise reduction is performed on the lubricating grease monitoring data, the white corrosion crack risk monitoring data, the pretightening force monitoring data and the embedded temperature monitoring data; and extracting corresponding order spectrum characteristics from the vibration monitoring data during characteristic extraction, and extracting noise-reduced data from the lubricating grease monitoring data, the white corrosion crack risk monitoring data, the pretightening force monitoring data and the embedded temperature monitoring data. Firstly, data cleaning is carried out on collected signals of each data source, and relevant data are removed when the data collected at adjacent moments have large fluctuation; when noise reduction is carried out, noise reduction is carried out on the vibration monitoring data by adopting a variational modal decomposition algorithm, and median filtering noise reduction is carried out on the lubricating grease monitoring data, the white corrosion crack risk monitoring data, the pretightening force monitoring data and the embedded temperature monitoring data; and extracting corresponding order spectrum characteristics from the vibration monitoring data during characteristic extraction, and extracting noise-reduced data from the lubricating grease monitoring data, the white corrosion crack risk monitoring data, the pretightening force monitoring data and the embedded temperature monitoring data.
S3: as shown in fig. 2, inputting the signal characteristics processed by S2 into a fan main bearing health degree evaluation model, and outputting a fan main bearing comprehensive health index; the health degree evaluation model of the main bearing of the fan is established based on a back propagation neural network algorithm. The training method of the health degree evaluation model of the main bearing of the fan comprises the following steps: the method comprises the steps of collecting multiple groups of data under different conditions of normal operation of a fan main bearing, poor grease lubrication, white corrosion crack generation and bearing roller abrasion respectively, extracting corresponding data signal characteristics as input vectors according to different rotating speeds, marking the output operation health degree according to experience, inputting the collected data characteristics into a fan main bearing health degree evaluation model, setting hidden layers to be 3 and total layers to be 5 according to the number of input parameters, and adjusting the weight of each layer through a back propagation algorithm to obtain a trained fan main bearing health degree evaluation model.
S4: and comparing the comprehensive health index of the fan main bearing obtained in the step S3 with a calibrated threshold interval, determining the threshold interval where the comprehensive health index of the fan main bearing is located, finishing health degree evaluation, and adopting operation and maintenance strategies of different degrees according to health degree evaluation results. The threshold interval is divided into a good interval, a good interval and a medium interval, wherein the operation and maintenance strategy adopted in the good interval is only marked, the operation and maintenance strategy adopted in the good interval is continuous observation, the operation and maintenance strategy adopted in the medium interval is on-site confirmation, and the operation and maintenance strategy adopted in the poor interval is shutdown inspection.
As a preferable embodiment of the present invention, S4 is followed by: and (5) carrying out posterior analysis on the health degree evaluation result of the S4, and carrying out correction optimization on the health degree evaluation model of the fan main bearing in the S3 as a historical record after secondary confirmation and annotation.
The invention discloses a fan bearing operation health degree evaluation system based on multi-source data, which comprises the following steps:
the monitoring data source acquisition module is used for acquiring information of a plurality of monitoring data sources of the fan main bearing;
the monitoring data source signal processing module is used for carrying out noise reduction and feature extraction on the acquired signals of all data sources;
the fan main bearing comprehensive health index output module inputs the processed signal characteristics into the fan main bearing health degree evaluation model and outputs fan main bearing comprehensive health indexes;
and the health degree evaluation and operation and maintenance strategy matching module is used for comparing the obtained comprehensive health index of the fan main bearing with a calibrated threshold interval, determining the threshold interval where the comprehensive health index of the fan main bearing is located, finishing health degree evaluation, and matching operation and maintenance strategies of different degrees according to the health degree evaluation result.
The invention is further illustrated below by means of a specific example:
the invention provides a flow schematic diagram of a method for evaluating the running health degree of a main bearing of a fan based on multi-source data, which comprises the following steps:
first, information of a plurality of monitoring data sources of a main bearing is obtained. The method comprises a plurality of monitoring data sources such as lubricating grease monitoring data { O }, white corrosion crack risk monitoring data { W }, pretightening force monitoring data { P }, embedded temperature monitoring data { T }, vibration monitoring data { Z }, and the like. The lubricating grease monitoring data comprises the water content Ow and the temperature Ot of the grease; the white corrosion crack monitoring data comprise humidity Wh and temperature Wt in the operating environment of the main bearing, shaft voltage Wv and partial discharge Wu; the pretightening force monitoring data comprise pretightening forces Pi and Po inwards of the side surfaces of the inner ring and the outer ring of the bearing; the embedded temperature monitoring data comprises the surface temperature Ti of the side surface of the inner ring of the main bearing; the vibration monitoring data includes vibration amplitude frequencies Za and Zf disposed at a plurality of detection locations. The same acquisition clock is adopted during acquisition, so that the synchronism of data acquisition is ensured.
Secondly, the signals { O }, { W }, { P }, { T }, and { Z } of each acquisition data source are subjected to noise reduction and feature extraction through a signal processing technology. Firstly, cleaning data, and eliminating relevant data when the data acquired at adjacent moments of the following data have large fluctuation: the water content Ow and the temperature Ot of the grease, the humidity Wh and the temperature Wt in the operating environment of the main bearing, the shaft voltage Wv, the partial discharge Wh, the inward pretightening force Pi and Po of the side surface of the inner ring and the outer ring of the main bearing, the surface temperature Ti of the side surface of the inner ring of the main bearing, and the vibration amplitude frequencies Za and Zf. And (3) denoising the vibration monitoring data Za and Zf by adopting a variational modal decomposition algorithm, and performing median filtering denoising on other monitoring data. Corresponding order spectrum features Zsm and Zsf are extracted from the vibration monitoring data Za and Zf, and data subjected to noise reduction are extracted from other monitoring data sources.
Thirdly, the extracted signal features of the multi-source data are input to the health assessment model Mh, and { Ow, Ot, Wh, Wt, Wv, Wh, Pi, Po, Ti, Zsm, Zsf } are used as input vectors of the model. And outputting the comprehensive health index Hc of the main bearing of the fan by the health degree evaluation model Mh. The evaluation model is based on a Back Propagation Neural Network (BPNN) algorithm.
Fourthly, the health degree index Hc output by the evaluation model is compared with a calibration threshold interval { [ Hcd, Hcu ] i } (i is 1 to n), the threshold interval is divided into n intervals according to actual needs, the threshold interval can be divided into 4 intervals according to conditions such as excellent, good, medium and poor, and operation and maintenance strategies of different degrees are adopted according to the threshold interval in which the output index is located. Such as a check for downtime, confirmation in the field, continued observation, or simply marking.
Fifthly, carrying out posterior analysis on the health degree evaluation result Hc, and carrying out correction optimization Mh on the evaluation model as a history record after secondary confirmation and labeling.
In the third step of the invention, an evaluation model Mh needs to be trained, multiple groups of data { Ow, Ot, Wh, Wt, Wv, Wh, Pi, Po, Ti, Zsm, Zsf } under different conditions such as normal operation of a main bearing of the fan, poor grease lubrication, occurrence of white corrosion cracks, abrasion of a bearing roller and the like are respectively acquired, corresponding data signal characteristics are extracted according to different rotating speeds to serve as input vectors, the output operation health degree is labeled according to experience, then the acquired data characteristics are input into the evaluation model Mh, a hidden layer is set to be 3 according to the number of input parameters, the total number of layers of the evaluation model Mh is 5, and the weight of each layer is adjusted through a back propagation algorithm to obtain the trained evaluation model Mh.
It should be noted that the above description is only a part of the embodiments of the present invention, and equivalent changes made to the system described in the present invention are included in the protection scope of the present invention. It will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (10)
1. The utility model provides a fan bearing operation health degree assessment method based on multisource data which characterized in that includes:
s1: collecting information of a plurality of monitoring data sources of a main bearing of a fan;
s2: carrying out noise reduction and feature extraction on the signals of the data sources acquired in the step S1;
s3: inputting the signal characteristics processed by the S2 into a fan main bearing health degree evaluation model, and outputting a fan main bearing comprehensive health index;
s4: and comparing the comprehensive health index of the fan main bearing obtained in the step S3 with a calibrated threshold interval, determining the threshold interval where the comprehensive health index of the fan main bearing is located, finishing health degree evaluation, and adopting operation and maintenance strategies of different degrees according to health degree evaluation results.
2. The multi-source data-based fan bearing operation health assessment method according to claim 1, wherein in S1, the monitoring data sources include lubricating grease monitoring data, white corrosion crack risk monitoring data, pre-tightening force monitoring data, embedded temperature monitoring data and vibration monitoring data.
3. A multi-source data-based fan bearing operational health assessment method as claimed in claim 2, wherein the grease monitoring data includes water content and temperature of grease; the white corrosion crack monitoring data comprise humidity and temperature in the operating environment of the main bearing, shaft voltage and partial discharge; the pretightening force monitoring data comprises inward pretightening force of the side surfaces of the inner ring and the outer ring of the bearing; the embedded temperature monitoring data comprises the surface temperature of the side surface of the inner ring of the main bearing; the vibration monitoring data includes vibration amplitude frequencies deployed at a plurality of detection locations.
4. The multi-source data-based fan bearing operation health assessment method according to claim 2, wherein in S2, firstly, data cleaning is performed on the signals of the acquired data sources, and relevant data are removed when the data acquired at adjacent moments have large fluctuation; when in noise reduction, the vibration monitoring data is subjected to noise reduction by adopting a variational modal decomposition algorithm, and median filtering noise reduction is performed on the lubricating grease monitoring data, the white corrosion crack risk monitoring data, the pretightening force monitoring data and the embedded temperature monitoring data; and extracting corresponding order spectrum characteristics from the vibration monitoring data during characteristic extraction, and extracting noise-reduced data from the lubricating grease monitoring data, the white corrosion crack risk monitoring data, the pretightening force monitoring data and the embedded temperature monitoring data.
5. The multi-source data-based fan bearing operating health assessment method of claim 2, wherein all monitoring data is collected under the same collection clock.
6. The multi-source data-based fan bearing operation health assessment method of claim 1, wherein in S3, the fan bearing health assessment model is established based on a back propagation neural network algorithm.
7. The multi-source data based fan bearing operation health assessment method of claim 1, wherein the fan bearing health assessment model in S3 is trained by the following method: the method comprises the steps of collecting multiple groups of data under different conditions of normal operation of a fan main bearing, poor grease lubrication, white corrosion crack generation and bearing roller abrasion respectively, extracting corresponding data signal characteristics as input vectors according to different rotating speeds, marking the output operation health degree according to experience, inputting the collected data characteristics into a fan main bearing health degree evaluation model, setting hidden layers to be 3 and total layers to be 5 according to the number of input parameters, and adjusting the weight of each layer through a back propagation algorithm to obtain a trained fan main bearing health degree evaluation model.
8. The multi-source data-based fan bearing operation health assessment method of claim 1, wherein in S4, the threshold interval is divided into a good interval, a medium interval and a poor interval, wherein the operation and maintenance strategy adopted in the good interval is only marked, the operation and maintenance strategy adopted in the good interval is continuous observation, the operation and maintenance strategy adopted in the medium interval is field confirmation, and the operation and maintenance strategy adopted in the poor interval is shutdown inspection.
9. The multi-source data-based fan bearing operating health assessment method of claim 1, further comprising after S4: and (4) carrying out posterior analysis on the health degree evaluation result of the S4, and carrying out correction optimization on the health degree evaluation model of the fan main bearing in the S3 as a history record after secondary confirmation and annotation.
10. The utility model provides a fan bearing operation health evaluation system based on multisource data which characterized in that includes:
the monitoring data source acquisition module is used for acquiring information of a plurality of monitoring data sources of the fan main bearing;
the monitoring data source signal processing module is used for carrying out noise reduction and feature extraction on the acquired signals of all data sources;
the fan main bearing comprehensive health index output module inputs the processed signal characteristics into the fan main bearing health degree evaluation model and outputs fan main bearing comprehensive health indexes;
and the health degree evaluation and operation and maintenance strategy matching module is used for comparing the obtained comprehensive health index of the fan main bearing with a calibrated threshold interval, determining the threshold interval where the comprehensive health index of the fan main bearing is located, finishing health degree evaluation, and matching operation and maintenance strategies of different degrees according to the health degree evaluation result.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210720237.1A CN115060491A (en) | 2022-06-23 | 2022-06-23 | Fan bearing operation health degree assessment method and system based on multi-source data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210720237.1A CN115060491A (en) | 2022-06-23 | 2022-06-23 | Fan bearing operation health degree assessment method and system based on multi-source data |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115060491A true CN115060491A (en) | 2022-09-16 |
Family
ID=83202874
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210720237.1A Pending CN115060491A (en) | 2022-06-23 | 2022-06-23 | Fan bearing operation health degree assessment method and system based on multi-source data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115060491A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116221038A (en) * | 2023-05-10 | 2023-06-06 | 山东金帝精密机械科技股份有限公司 | Bearing operation monitoring method and device based on wind power bearing retainer |
CN116257739A (en) * | 2023-05-16 | 2023-06-13 | 成都飞机工业(集团)有限责任公司 | Rapid visual diagnosis method for high-speed motorized spindle |
CN116773168A (en) * | 2023-06-20 | 2023-09-19 | 南通思诺船舶科技有限公司 | Method and system for diagnosing faults of propeller shaft |
-
2022
- 2022-06-23 CN CN202210720237.1A patent/CN115060491A/en active Pending
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116221038A (en) * | 2023-05-10 | 2023-06-06 | 山东金帝精密机械科技股份有限公司 | Bearing operation monitoring method and device based on wind power bearing retainer |
CN116257739A (en) * | 2023-05-16 | 2023-06-13 | 成都飞机工业(集团)有限责任公司 | Rapid visual diagnosis method for high-speed motorized spindle |
CN116257739B (en) * | 2023-05-16 | 2023-08-04 | 成都飞机工业(集团)有限责任公司 | Rapid visual diagnosis method for high-speed motorized spindle |
CN116773168A (en) * | 2023-06-20 | 2023-09-19 | 南通思诺船舶科技有限公司 | Method and system for diagnosing faults of propeller shaft |
CN116773168B (en) * | 2023-06-20 | 2024-03-12 | 南通思诺船舶科技有限公司 | Method and system for diagnosing faults of propeller shaft |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN115060491A (en) | Fan bearing operation health degree assessment method and system based on multi-source data | |
Saufi et al. | Challenges and opportunities of deep learning models for machinery fault detection and diagnosis: A review | |
Cui et al. | An anomaly detection approach based on machine learning and scada data for condition monitoring of wind turbines | |
CN111922095A (en) | Vibration diagnosis method for abnormal torsional vibration fault of roller of cold rolling mill | |
Barbieri et al. | Analysis of automotive gearbox faults using vibration signal | |
CN112179691A (en) | Mechanical equipment running state abnormity detection system and method based on counterstudy strategy | |
EP3788328B1 (en) | System and process for pattern matching bearing vibration diagnostics | |
Cui et al. | An anomaly detection approach using wavelet transform and artificial neural networks for condition monitoring of wind turbines' gearboxes | |
CN112660745A (en) | Intelligent diagnosis method and system for carrier roller fault and readable storage medium | |
CN111103137A (en) | Wind turbine gearbox fault diagnosis method based on deep neural network | |
CN109255333A (en) | A kind of large-scale wind electricity unit rolling bearing fault Hybrid approaches of diagnosis | |
Zhu et al. | Operational state assessment of wind turbine gearbox based on long short-term memory networks and fuzzy synthesis | |
CN114881087A (en) | Building robot bearing performance degradation assessment method | |
CN113516159B (en) | Rail vehicle running part pinion shaft crack fault diagnosis method and system | |
CN117093938A (en) | Fan bearing fault detection method and system based on deep learning | |
Elijorde et al. | A wind turbine fault detection approach based on cluster analysis and frequent pattern mining | |
Lv et al. | A new feature extraction technique for early degeneration detection of rolling bearings | |
CN117034001A (en) | Wind turbine generator system fault prediction method and device and electronic equipment | |
CN110794683A (en) | Wind power gear box state evaluation method based on deep neural network and kurtosis characteristics | |
CN115165364A (en) | Wind turbine generator bearing fault diagnosis model construction method based on transfer learning | |
US11339763B2 (en) | Method for windmill farm monitoring | |
Orsagh et al. | Advanced vibration monitoring for wind turbine health management | |
Sato et al. | Degradation estimation of turbines in wind farm using denoising autoencoder model | |
CN115326393A (en) | Wind turbine generator bearing pair fault diagnosis method based on temperature information | |
CN111075661B (en) | Method for judging health condition of main shaft bearing of wind turbine generator based on temperature change trend |
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 |