CN106053090A - Neighbor abnormal detection system of gas turbine - Google Patents
Neighbor abnormal detection system of gas turbine Download PDFInfo
- Publication number
- CN106053090A CN106053090A CN201610698009.3A CN201610698009A CN106053090A CN 106053090 A CN106053090 A CN 106053090A CN 201610698009 A CN201610698009 A CN 201610698009A CN 106053090 A CN106053090 A CN 106053090A
- Authority
- CN
- China
- Prior art keywords
- data
- degree
- directions
- sample
- vibration
- 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
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
- G01M15/00—Testing of engines
- G01M15/14—Testing gas-turbine engines or jet-propulsion engines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The invention belongs to the technical field of gas turbine equipment and specifically relates to a neighbor abnormal detection system of a gas turbine. The system comprises the implementation steps of: obtaining monitoring data and input parameters; extracting characteristic quantities representing different moment characteristics; establishing a global distance matrix measuring similarity among the sample points at different moments; obtaining a local reachable density of each sample from G samples and a set of neighbor sample points; comparing the local reachable density of each sample with that of other samples in a neighbor domain, and calculating an abnormal score of each sample; and ordering the amounts of the abnormal score results of the samples, and obtaining a set of abnormal samples. According to the invention, the requirement on calculation resources is low, the time and space cost is relatively low, the data is rapidly calculated based on a linear calculation mode, the abnormal data points are finally expressed, and the accountability is high.
Description
Technical field:
The invention belongs to gas-turbine plant technical field, be specifically related to neighbour's abnormality detection system of a kind of gas turbine.
Background technology:
Gas turbine as a kind of important huge dynamic power machine, have compact conformation, operate steadily, the more high spy of the thermal efficiency
Point, range of application is the most extensive.In reality, the safe and reliable job requirement to gas turbine is the highest, daily at gas turbine
Under working condition, the health condition of unit is analyzed monitoring, the various abnormal conditions being likely to occur is analyzed detection,
Can avoid or so that process the large-scale fault of combustion engine in time.Current all gas turbine manufacturers have all installed additional more on turbine
Sensor with monitor turbine duty.The data message (such as combustion engine rotating speed, out temperature etc.) of monitoring record, to wheel
The operational support of machine is significant and use value.But the data message amount of sensor acquisition is huge, and noise is the most more,
The quality of data is the highest.The quantity of sensor is various simultaneously, and the general pre-analytic intensity judged is the biggest, to all the sensors
Information carries out the calculating of pre-identification and analysis load is very big, and analysis efficiency is the lowest, and degree of erroneous judgement by accident can be the highest.Thus be the most right
The health monitoring of the system information of the high complexity of the magnanimity of the heavy duty industrial equipment such as gas turbine and fault anticipation, need to tie simultaneously
Each advanced technology of the substitutive characteristics and data process that close turbine object is carried out.
Summary of the invention:
The data number that the present invention is to solve the sensor acquisition of existing gas turbine is numerous, quantity of information is the hugest, pre-
Alert technical deficiency, the problem that level of fault diagnosis is the most limited, erroneous judgement degree is high, it is provided that neighbour's abnormality detection of a kind of gas turbine
System and detection method, can promote on a large scale and use.
The technical solution used in the present invention is: neighbour's abnormality detection system of a kind of gas turbine, and this detecting system includes
Data interface module, feature extraction module, similarity measure module, Density Metric module, Outlier factor module and abnormal evaluation mould
Block.
The detection method step of this detecting system is as follows:
Step one, by data interface module obtain Monitoring Data and input parameter
From the monitoring of software of gas turbine, obtain G Monitoring Data the most in the same time, below use PkRepresent theThe prison in individual moment
Measured value, wherein 1≤k≤G;And input parameter: neighborhood number of objects, abnormal with reference to ratio beta;
Step 2, extracted the characteristic quantity characterizing variant moment characteristic by feature extraction module
Characteristic quantity is selected from Monitoring Data, wherein 1≤≤ 29, the i.e. corresponding value including following 29 measuring points: gear-box
Vibration, electromotor DEX vibration, electromotor DEY vibration, electromotor EEX vibration, electromotor EEY vibration, gasifier speed,
The total actual power of electromotor, 3# bearing Y vibrate, 3# bearing X vibrates, 2# bearing Y vibrates, 2# bearing X vibrates, 1# bearing Y vibrates,
1# bearing X vibration, compressor air inlet temperature, average exhaust temperature, the delivery temperature in 0 degree of direction, the aerofluxus in 30 degree of directions
Temperature, the delivery temperature in 60 degree of directions, the delivery temperature in 90 degree of directions, the delivery temperature in 120 degree of directions, the row in 150 degree of directions
Temperature, the delivery temperature in 180 degree of directions, the delivery temperature in 210 degree of directions, the delivery temperature in 240 degree of directions, 270 degree of directions
Delivery temperature, the delivery temperature in 300 degree of directions, the delivery temperature in 330 degree of directions, the oil temperature of lubricating oil system import and lubrication
The oil temperature of the outlet of oil system,For the kth momentThe Monitoring Data of individual measuring point;
Step 3, set up the overall distance matrix of similarity between tolerance sample point the most in the same time by similarity measure module
The similarity distance between data and the data in g moment in b moment is measured by p norm distance, b=1,2 ..., G, g=1,2 ..., G, and set up overall situation distance matrix,
,
Wherein,For the said two momentWith?The distance of individual characteristic quantity calculates weights, takesFor?Individual dimension
Tolerance,Being the feature weight vector of 29 dimensions, when not setting, acquiescence takesIt it is all the column vector of 1 for all numerical value;
Step 4, by Density Metric module obtain sample set Neighbourhood set NB and local reachability density vector LRS
Wherein Neighbourhood set, sample'sNeighbourhood set is;Up to density
Vector, sampleLocal reachability density be labeled as,
Single sampleNeighbourhood setUp to densityPreparation method be:
(1), sample is obtainedAnd between other sampleNear distance, is designated as,
The most right
By being ranked up from small to large, corresponding theLittle distance is;Wherein withBefore closestIndividual sampleSet is designated as, as follows
(2),The local reachability density of individual sampleIt is calculated as;
Step 5, by Outlier factor module obtain all samples local outlier factor coefficient, Qi ZhongThe office of individual sample
Portion's Outlier factor is designated as, computing formula is as follows
, whereinFor withBefore closestIndividual sample;
Step 6, by abnormal assessment module, sample is carried out abnormal evaluation
First being ranked up the number of cluster result, draw the set of exceptional sample, the sample meeting description below is i.e. abnormal
Sample: to allValue is ranked up by order from big to small, then beforeThe sample point that individual value is corresponding, it is i.e.
Abnormal data.
The monitoring feature amount in each momentIt is made up of following characteristics amount: gear-box vibration data, electromotor
DEX vibration data, electromotor DEY vibration data, electromotor EEX vibration data, electromotor EEY shakes
Dynamic data, gasifier speed data, electromotor total actual power data, 3# bearing Y vibration number
According to, 3# bearing X vibration data, 2# bearing Y vibration data, 2# bearing X vibration data、1#
Bearing Y vibration data, 1# bearing X vibration data, compressor air inlet temperature data, aerofluxus
Average temperature data, the exhaust temperature data in 0 degree of direction, the exhaust temperature data in 30 degree of directions
, the exhaust temperature data in 60 degree of directions, the exhaust temperature data in 90 degree of directions, the aerofluxus temperature in 120 degree of directions
Degrees of data, the exhaust temperature data in 150 degree of directions, the exhaust temperature data in 180 degree of directions、
The exhaust temperature data in 210 degree of directions, the exhaust temperature data in 240 degree of directions, the aerofluxus in 270 degree of directions
Temperature data, the exhaust temperature data in 300 degree of directions, the exhaust temperature data in 330 degree of directions、
The oil temperature data of lubricating oil system importAnd the oil temperature data of the outlet of lubricating oil system。
Neighborhood number of objects in described step oneFor integer, the abnormal span with reference to ratio beta is 0 < β < 1.
Beneficial effects of the present invention: the present invention is the abnormality detection system of the quick clustering of a kind of gas turbine, be based on
The intrinsic characteristic of gas turbine, proposes a kind of method for detecting abnormality based on statistical nature, in process based onNorm distance is entered
Row similarity definition, and the algorithm of linear complexity is analyzed, computational resource requirements is little, has relatively low time and space
Cost;The calculation cost of abnormality detecting process is the lowest, finally by the density anomaly degree with neighbor point with abnormal expression data point,
Have the strongest can be illustrative, this abnormality detection mode more has practical value in reality.
Accompanying drawing illustrates:
Fig. 1 is module composition and the FB(flow block) of process step of the present invention.
Fig. 2 is that the Monitoring Data of the present invention obtains flow chart
Fig. 3 is to set up overall situation Distance matrix D in the present inventionG×GFlow chart
Detailed description of the invention:
With reference to each figure, neighbour's abnormality detection system of a kind of gas turbine, this detecting system includes that data interface module, feature are taken out
Delivery block, similarity measure module, Density Metric module, Outlier factor module and abnormal assessment module.
The detection method step of this detecting system is as follows:
Step one, by data interface module obtain Monitoring Data and input parameter
From the monitoring of software of gas turbine, obtain G Monitoring Data the most in the same time, below use PkRepresent theThe prison in individual moment
Measured value, wherein 1≤k≤G;And input parameter: neighborhood number of objects, abnormal with reference to ratio beta;
Step 2, extracted the characteristic quantity characterizing variant moment characteristic by feature extraction module
Characteristic quantity is selected from Monitoring Data, wherein 1≤≤ 29, the i.e. corresponding value including following 29 measuring points: gear-box
Vibration, electromotor DEX vibration, electromotor DEY vibration, electromotor EEX vibration, electromotor EEY vibration, gasifier speed,
The total actual power of electromotor, 3# bearing Y vibrate, 3# bearing X vibrates, 2# bearing Y vibrates, 2# bearing X vibrates, 1# bearing Y vibrates,
1# bearing X vibration, compressor air inlet temperature, average exhaust temperature, the delivery temperature in 0 degree of direction, the aerofluxus in 30 degree of directions
Temperature, the delivery temperature in 60 degree of directions, the delivery temperature in 90 degree of directions, the delivery temperature in 120 degree of directions, the row in 150 degree of directions
Temperature, the delivery temperature in 180 degree of directions, the delivery temperature in 210 degree of directions, the delivery temperature in 240 degree of directions, 270 degree of directions
Delivery temperature, the delivery temperature in 300 degree of directions, the delivery temperature in 330 degree of directions, the oil temperature of lubricating oil system import and lubrication
The oil temperature of the outlet of oil system,For the kth momentThe Monitoring Data of individual measuring point;
Step 3, set up the overall distance matrix of similarity between tolerance sample point the most in the same time by similarity measure module
The similarity distance between data and the data in g moment in b moment is measured by p norm distance, b=1,2 ..., G, g=1,2 ..., G, and set up overall situation distance matrix,
,
Wherein,For the said two momentWith?The distance of individual characteristic quantity calculates weights, takesFor?Individual dimension
Tolerance,Being the feature weight vector of 29 dimensions, when not setting, acquiescence takesIt it is all the column vector of 1 for all numerical value;
Step 4, by Density Metric module obtain sample set Neighbourhood set NB and local reachability density vector LRS
Wherein Neighbourhood set, sample'sNeighbourhood set is;Up to density
Vector, sampleLocal reachability density be labeled as,
Single sampleNeighbourhood setUp to densityPreparation method be:
(1), sample is obtainedAnd between other sampleNear distance, is designated as,
The most right
By being ranked up from small to large, corresponding theLittle distance is;Wherein withBefore closestIndividual sampleSet is designated as, as follows
(2),The local reachability density of individual sampleIt is calculated as;
Step 5, by Outlier factor module obtain all samples local outlier factor coefficient, Qi ZhongThe office of individual sample
Portion's Outlier factor is designated as, computing formula is as follows
, whereinFor withBefore closestIndividual sample;
Step 6, by abnormal assessment module, sample is carried out abnormal evaluation
First being ranked up the number of cluster result, draw the set of exceptional sample, the sample meeting description below is i.e. abnormal
Sample: to allValue is ranked up by order from big to small, then beforeThe sample point that individual value is corresponding, it is i.e.
Abnormal data.
The monitoring feature amount in each momentIt is made up of following characteristics amount: gear-box vibration data, electromotor
DEX vibration data, electromotor DEY vibration data, electromotor EEX vibration data, electromotor EEY shakes
Dynamic data, gasifier speed data, electromotor total actual power data, 3# bearing Y vibration number
According to, 3# bearing X vibration data, 2# bearing Y vibration data, 2# bearing X vibration data、1#
Bearing Y vibration data, 1# bearing X vibration data, compressor air inlet temperature data, aerofluxus
Average temperature data, the exhaust temperature data in 0 degree of direction, the exhaust temperature data in 30 degree of directions
, the exhaust temperature data in 60 degree of directions, the exhaust temperature data in 90 degree of directions, the aerofluxus temperature in 120 degree of directions
Degrees of data, the exhaust temperature data in 150 degree of directions, the exhaust temperature data in 180 degree of directions、
The exhaust temperature data in 210 degree of directions, the exhaust temperature data in 240 degree of directions, the aerofluxus in 270 degree of directions
Temperature data, the exhaust temperature data in 300 degree of directions, the exhaust temperature data in 330 degree of directions、
The oil temperature data of lubricating oil system importAnd the oil temperature data of the outlet of lubricating oil system。
Neighborhood number of objects in described step oneFor integer, the abnormal span with reference to ratio beta is 0 < β < 1.
Claims (4)
1. neighbour's abnormality detection system of a gas turbine, it is characterised in that: this detecting system includes data interface module, spy
Levy abstraction module, similarity measure module, Density Metric module, Outlier factor module and abnormal assessment module.
Neighbour's abnormality detection system of a kind of gas turbine the most according to claim 1, it is characterised in that: this detecting system
Detection method as follows:
Step one, by data interface module obtain Monitoring Data and input parameter
From the monitoring of software of gas turbine, obtain G Monitoring Data the most in the same time, below use PkRepresent theThe prison in individual moment
Measured value, wherein 1≤k≤G;And input parameter: neighborhood number of objects, abnormal with reference to ratio beta;
Step 2, extracted the characteristic quantity characterizing variant moment characteristic by feature extraction module
Characteristic quantity is selected from Monitoring Data, wherein 1≤≤ 29, the i.e. corresponding value including following 29 measuring points: gear-box
Vibration, electromotor DEX vibration, electromotor DEY vibration, electromotor EEX vibration, electromotor EEY vibration, gasifier speed,
The total actual power of electromotor, 3# bearing Y vibrate, 3# bearing X vibrates, 2# bearing Y vibrates, 2# bearing X vibrates, 1# bearing Y vibrates,
1# bearing X vibration, compressor air inlet temperature, average exhaust temperature, the delivery temperature in 0 degree of direction, the aerofluxus in 30 degree of directions
Temperature, the delivery temperature in 60 degree of directions, the delivery temperature in 90 degree of directions, the delivery temperature in 120 degree of directions, the row in 150 degree of directions
Temperature, the delivery temperature in 180 degree of directions, the delivery temperature in 210 degree of directions, the delivery temperature in 240 degree of directions, 270 degree of directions
Delivery temperature, the delivery temperature in 300 degree of directions, the delivery temperature in 330 degree of directions, the oil temperature of lubricating oil system import and lubrication
The oil temperature of the outlet of oil system,For the kth momentThe Monitoring Data of individual measuring point;
Step 3, set up the overall distance matrix of similarity between tolerance sample point the most in the same time by similarity measure module
The similarity distance between data and the data in g moment in b moment is measured by p norm distance, b=1,2 ..., G, g=1,2 ..., G, and set up overall situation distance matrix,
,
Wherein,For the said two momentWith?The distance of individual characteristic quantity calculates weights, takesFor?Individual dimension
Amount,Being the feature weight vector of 29 dimensions, when not setting, acquiescence takesIt it is all the column vector of 1 for all numerical value;
Step 4, by Density Metric module obtain sample set Neighbourhood set NB and local reachability density vector LRS
Wherein Neighbourhood set, sample'sNeighbourhood set is;Up to density to
Amount, sampleLocal reachability density be labeled as, single
Individual sampleNeighbourhood setUp to densityPreparation method be:
(1), sample is obtainedAnd between other sampleNear distance, is designated as,
The most right
By being ranked up from small to large, corresponding theLittle distance is;Wherein withBefore closestIndividual sampleSet is designated as, as follows
(2),The local reachability density of individual sampleIt is calculated as;
Step 5, by Outlier factor module obtain all samples local outlier factor coefficient, Qi ZhongThe local of individual sample
Outlier factor is designated as, computing formula is as follows
, whereinFor withBefore closestIndividual sample;
Step 6, by abnormal assessment module, sample is carried out abnormal evaluation
First being ranked up the number of cluster result, draw the set of exceptional sample, the sample meeting description below is i.e. abnormal
Sample: to allValue is ranked up by order from big to small, then beforeThe sample point that individual value is corresponding, it is i.e.
Abnormal data.
Neighbour's abnormality detection system of a kind of gas turbine the most according to claim 2, it is characterised in that: each moment
Monitoring feature amountIt is made up of following characteristics amount: gear-box vibration data, electromotor DEX vibration data、
Electromotor DEY vibration data, electromotor EEX vibration data, electromotor EEY vibration data, combustion gas sends out
Raw device rotary speed data, electromotor total actual power data, 3# bearing Y vibration data, 3# bearing X shakes
Dynamic data, 2# bearing Y vibration data, 2# bearing X vibration data, 1# bearing Y vibration data, 1# bearing X vibration data, compressor air inlet temperature data, average exhaust temperature data, the exhaust temperature data in 0 degree of direction, the exhaust temperature data in 30 degree of directions, 60 degree of directions
Exhaust temperature data, the exhaust temperature data in 90 degree of directions, the exhaust temperature data in 120 degree of directions, the exhaust temperature data in 150 degree of directions, the exhaust temperature data in 180 degree of directions, 210 degree of sides
To exhaust temperature data, the exhaust temperature data in 240 degree of directions, the exhaust temperature data in 270 degree of directions, the exhaust temperature data in 300 degree of directions, the exhaust temperature data in 330 degree of directions, lubricating oil system
The oil temperature data of system importAnd the oil temperature data of the outlet of lubricating oil system。
Neighbour's abnormality detection system of a kind of gas turbine the most according to claim 2, it is characterised in that: described step one
In neighborhood number of objectsFor integer, the abnormal span with reference to ratio beta is 0 < β < 1.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610698009.3A CN106053090A (en) | 2016-08-22 | 2016-08-22 | Neighbor abnormal detection system of gas turbine |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610698009.3A CN106053090A (en) | 2016-08-22 | 2016-08-22 | Neighbor abnormal detection system of gas turbine |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106053090A true CN106053090A (en) | 2016-10-26 |
Family
ID=57195379
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610698009.3A Pending CN106053090A (en) | 2016-08-22 | 2016-08-22 | Neighbor abnormal detection system of gas turbine |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106053090A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107271194A (en) * | 2017-06-14 | 2017-10-20 | 华电电力科学研究院 | Gas turbine blower vibration test platform |
CN108304350A (en) * | 2017-12-25 | 2018-07-20 | 明阳智慧能源集团股份公司 | Wind turbine index prediction based on large data sets neighbour's strategy and fault early warning method |
CN108563217A (en) * | 2018-05-29 | 2018-09-21 | 济南浪潮高新科技投资发展有限公司 | The robust method for detecting abnormality analyzed based on part and global statistics |
CN110864887A (en) * | 2019-11-19 | 2020-03-06 | 北京瑞莱智慧科技有限公司 | Method, device, medium and computing equipment for determining operating condition of mechanical equipment |
CN117909692A (en) * | 2024-03-18 | 2024-04-19 | 山东海纳智能装备科技股份有限公司 | Intelligent analysis method for operation data of double-disc motor bearing |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102706563A (en) * | 2012-06-14 | 2012-10-03 | 哈尔滨工业大学 | Detection method for neighbor abnormities of gas turbine |
-
2016
- 2016-08-22 CN CN201610698009.3A patent/CN106053090A/en active Pending
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102706563A (en) * | 2012-06-14 | 2012-10-03 | 哈尔滨工业大学 | Detection method for neighbor abnormities of gas turbine |
Non-Patent Citations (3)
Title |
---|
周大镯 等: "时间序列增量异常模式检测算法", 《计算机工程》 * |
解亚萍: "基于测控系统的软件检测技术", 《信息与电脑》 * |
马捷中 等: "测控软件系统检测技术研究", 《计算机应用与软件》 * |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107271194A (en) * | 2017-06-14 | 2017-10-20 | 华电电力科学研究院 | Gas turbine blower vibration test platform |
CN108304350A (en) * | 2017-12-25 | 2018-07-20 | 明阳智慧能源集团股份公司 | Wind turbine index prediction based on large data sets neighbour's strategy and fault early warning method |
CN108304350B (en) * | 2017-12-25 | 2021-04-30 | 明阳智慧能源集团股份公司 | Fan index prediction and fault early warning method based on big data set neighbor strategy |
CN108563217A (en) * | 2018-05-29 | 2018-09-21 | 济南浪潮高新科技投资发展有限公司 | The robust method for detecting abnormality analyzed based on part and global statistics |
CN110864887A (en) * | 2019-11-19 | 2020-03-06 | 北京瑞莱智慧科技有限公司 | Method, device, medium and computing equipment for determining operating condition of mechanical equipment |
CN117909692A (en) * | 2024-03-18 | 2024-04-19 | 山东海纳智能装备科技股份有限公司 | Intelligent analysis method for operation data of double-disc motor bearing |
CN117909692B (en) * | 2024-03-18 | 2024-05-31 | 山东海纳智能装备科技股份有限公司 | Intelligent analysis method for operation data of double-disc motor bearing |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106053090A (en) | Neighbor abnormal detection system of gas turbine | |
CN105804981B (en) | Motor train unit traction transformer oil pump remote failure monitors and early warning system and its method | |
CN103471841B (en) | A kind of rotating machinery vibrating failure diagnosis method | |
CN107489464B (en) | Steam turbine generator unit fault early warning method and system | |
CN102680235B (en) | Method and system for the analysis of turbine | |
KR20140130541A (en) | Method and system for advising operator action | |
CN102706563A (en) | Detection method for neighbor abnormities of gas turbine | |
CN109613428A (en) | It is a kind of can be as system and its application in motor device fault detection method | |
CN102607641A (en) | Cluster anomaly detection method of combustion gas turbine | |
CN108981796B (en) | Five-in-one hydraulic mechanical fault diagnosis method | |
CN105352586A (en) | Method used for realizing blade fatigue crack detection through resonance frequency detection | |
US8838398B2 (en) | Turbine-generator hydrogen seal oil system diagnosis | |
CN110050125A (en) | Information processing unit, information processing system, information processing method, program, substrate board treatment, reference data determination device and reference data determining method | |
Kumar et al. | A comprehensive review of conventional and intelligence-based approaches for the fault diagnosis and condition monitoring of induction motors | |
CN115614292B (en) | Vibration monitoring device and method for vertical water pump unit | |
CN110008898A (en) | Industrial equipment data edges processing method based on symbol and convolutional neural networks | |
CN102393303B (en) | Method for detecting abnormal sequencing of gas turbine engine | |
CN106762343A (en) | The diagnostic method of the hydraulic generator set thrust bearing failure based on online data | |
CN106053089A (en) | Ordering abnormal detection system of gas turbine | |
Kannan et al. | Nominal features-based class specific learning model for fault diagnosis in industrial applications | |
CN105865800A (en) | Gas turbine engine test bench testing system | |
Zhou et al. | Early warning analysis of online vibration fault characteristics of motor base screw loosening based on similarity measurement theory | |
He et al. | A review of optimal sensor deployment to diagnose manufacturing systems | |
Ceschini et al. | Detection and Classification of Sensor Anomalies in Gas Turbine Field Data | |
Deng et al. | A fractional hilbert transform order optimization algorithm based DE for bearing health monitoring |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20161026 |