CN110006655A - Aeroengine compressor monitoring method and monitoring system - Google Patents
Aeroengine compressor monitoring method and monitoring system Download PDFInfo
- Publication number
- CN110006655A CN110006655A CN201810010382.4A CN201810010382A CN110006655A CN 110006655 A CN110006655 A CN 110006655A CN 201810010382 A CN201810010382 A CN 201810010382A CN 110006655 A CN110006655 A CN 110006655A
- Authority
- CN
- China
- Prior art keywords
- stall
- signal
- low
- compressor
- aeroengine
- 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
- G01M15/02—Details or accessories of testing apparatus
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Control Of Positive-Displacement Air Blowers (AREA)
- Control Of Positive-Displacement Pumps (AREA)
Abstract
The purpose of the present invention is to provide a kind of aeroengine compressor monitoring method and monitoring systems, and aeroengine compressor monitoring can be realized by means of existing sensor, are easy to improve the aero-engine of existing military service or subsequent military service.Aeroengine compressor monitoring method according to an aspect of the present invention, comprising steps of obtaining the airborne vibration signal of the rotor of low-pressure compressor;The onboard features signal related with frequency and phase that characterization stall group movement velocity is lagged relative to rotor speed is extracted from the airborne vibration signal;Judge whether the low-pressure compressor handles stall conditions by the onboard features signal.
Description
Technical field
The present invention relates to aeroengine compressor monitoring method and monitoring systems.
Background technique
It is on active service the stage in aero-engine, it is necessary to which unexpected state (stall, surge) operation is in low-pressure compressor
Real-time monitoring is carried out, its severity is judged, takes counter-measure in time if necessary, such as deflates, reduction of speed or stop
Otherwise machine will lead to penalty even security events and occur.Currently to engine military service operational process mesolow compressor
Stall and the monitoring method of surge have no relevant publication, high-pressure compressor stall and surge monitoring are equal during engine is on active service
Using pressure sensor, the pulsation of compressor inlet and outlet pressure is measured, according to pressure fluctuation rule when stall or surge into
Row judgement.Pressure sensor is preferable for the monitoring degree of conformity of surge, because caused pressure fluctuation is in import and export when surge
Variation is obvious, but pressure sensor is lower to the monitoring accuracy of stall, because partial stall or rotating stall pass in and out compressor
Mouth pressure fluctuations are relatively small.For low-pressure compressor, by space and cost impact, it will not install airborne
Pressure sensor carries out pressure fluctuation monitoring to it, is unable to judge accurately whether low-pressure compressor occurs stall or surge.
US9624936B2 discloses a kind of method of Anti-surge Control for turbo-compressor, wherein in anti-surge control
Background vibration level is calculated based on first group of vibration data in selection frequency band in device processed;It can be grasped from least one vibrating sensor
Make ground to receive second group of vibration data in institute's surge-proofing controller, whether the turbo-compressor is in surging condition.
US20160103012A1 discloses a kind of method for monitoring surge condition, comprising: by the turbine
The vibration signal measured at least one position detects surge condition, wherein determining whether there is surge shape based on surge score
Condition.
US7677090B2 discloses the method and dress of the rotating stall in a kind of turbo blade for determining compressor
It sets, wherein monitoring blade passing frequency and associated vibrational energy judge stall: when the normal blade in compressor stage passes through
When vibrational energy is lower than scheduled first value under frequency, indicate the initial rotation stall in compressor stage logical higher than normal blade
While the blade passing frequency of overfrequency, vibrational energy rises to scheduled second value or more.
Above scheme is required to additionally increase sensor, is applied to ground experiment test truncation, can not or be difficult to quickly
It is convenient to be applied to existing military service engine.
Summary of the invention
The purpose of the present invention is to provide a kind of aeroengine compressor monitoring method and monitoring systems, can borrow
Help existing sensor and realize aeroengine compressor monitoring, is easy to the hair of the aviation to existing military service or subsequent military service
Motivation improves.
Aeroengine compressor monitoring method according to an aspect of the present invention, comprising the following steps:
Obtain the airborne vibration signal of the rotor of low-pressure compressor;
Characterization stall group movement velocity is lagged relative to rotor speed and frequency is extracted from the airborne vibration signal
Onboard features signal related with phase;
Judge whether the low-pressure compressor handles stall conditions by the onboard features signal.
One embodiment of the method further include:
The test vibration signal for obtaining the rotor of low-pressure compressor is tested by engine test;
Characterization stall group movement velocity is lagged relative to rotor speed and frequency is extracted from the test vibration signal
And/or the related assay features signal of phase, establish stall feature database;
The stall feature database is preset in controller;
The assay features signal of the onboard features signal Yu the stall feature database is compared, to judge that the low pressure is calmed the anger
Whether machine handles stall conditions.
In one embodiment of the method, the assay features signal includes stall limits value, stall alert value, root
It is limited according to the amplitude of the onboard features signal lower than the stall alert value, more than the stall alert value but lower than the stall
Value processed is more than the stall limits value, judge respectively the low-pressure compressor stall does not occur, stall occurs but it is not serious,
Pronounced stall occurs.
One embodiment of the method also by the airborne vibration signal judge low-pressure compressor whether surge.
The onboard features signal that one embodiment of the method is proposed in the process by engine movements, by certainly
Learning algorithm updates the stall feature database.
A kind of aeroengine compressor monitoring system according to a further aspect of the invention, including controller and airborne
Vibrating sensor, the controller include memory, processor and storage and can run on the memory and on the processor
Program, the processor executes following steps when executing described program:
Based on the monitoring of the airborne vibrating sensor, the airborne vibration signal of the rotor of low-pressure compressor is obtained;
Characterization stall group movement velocity is lagged relative to rotor speed and frequency is extracted from the airborne vibration signal
Onboard features signal related with phase;
Judge whether the low-pressure compressor handles stall conditions by the onboard features signal.
In one embodiment of the system, the processor also executes following steps when executing described program:
The stall feature database preset from one reads assay features signal;
The assay features signal of the onboard features signal Yu the stall feature database is compared, to judge that the low pressure is calmed the anger
Whether machine handles stall conditions.
In one embodiment of the system, the processor also executes following steps when executing described program:
The assay features signal includes stall limits value, stall alert value, according to the amplitude of the onboard features signal
Lower than the stall alert value, it is more than the stall alert value but is lower than the stall limits value, is more than the stall limits value,
Judge that stall, generation stall but not serious, generation pronounced stall do not occur for the low-pressure compressor respectively.
In one embodiment of the system, the processor also executes following steps when executing described program: passing through
The airborne vibration signal judge low-pressure compressor whether surge.
In one embodiment of the system, the processor also executes following steps when executing described program: passing through
The onboard features signal proposed during engine movements, updates the stall feature database by self-learning algorithm.
By rationally using existing airborne vibrating sensor, increasing the real time monitoring function to low-pressure compressor stall,
So that engine diagnosis function is more perfect, flight safety risk is reduced;This method or system make full use of existing airborne
Vibrating sensor does not need to increase new airborne pressure sensor, easily operated.
Detailed description of the invention
The above and other features of the present invention, property and advantage will pass through retouching with reference to the accompanying drawings and examples
It states and becomes readily apparent from, in which:
Fig. 1 is the stall Typical Vibration signal time-frequency characteristics extracted according to the present invention.
Fig. 2 is the flow chart of aeroengine compressor monitoring method according to the present invention.
Fig. 3 is the block diagram that aeroengine compressor according to the present invention monitors system.
Specific embodiment
The invention will be further described with attached drawing combined with specific embodiments below, elaborates in the following description more
Details to facilitate a thorough understanding of the present invention, still the present invention obviously can be come with a variety of other ways different from this description it is real
It applies, those skilled in the art can make similar popularization according to practical situations without violating the connotation of the present invention, drill
It unravels silk, therefore should not be limited the scope of the invention with the content of this specific embodiment.
The aftermentioned method rule of the vibration signal according to caused by low-pressure compressor stall and surge, by existing airborne vibration
Monitoring and comparison discovery low-pressure compressor stall and the surge in time of dynamic signal, and counter-measure is taken accordingly.Rotor fundamental frequency is
With the signal frequency of rotor speed signal same frequency.
Low pressure rotor level of vibration is monitored by airborne vibrating sensor, airborne vibrating sensor is in current motor mechanism
It is widely used in type, but and is not used for the monitoring of low-pressure compressor stall.
The research of people according to the present invention, when stall occurs for low-pressure compressor, it is certain poor that stall group relative rotor revolving speed has
It is different, and show as stall group relative rotor and circumferential movement occurs, the table on the rotor oscillation signal of airborne vibrating sensor monitoring
Now there is certain phase difference at the frequency signal of certain numerical value relationship, and with fundamental frequency signal with rotor fundamental frequency to exist.Stall
Phenomenon is that static pressure rises the end constantly increased in diffuser or leaf grating, the reason is that boundary-layer flow separation.Frequency and phase difference
It is different to change with specific engine, but the range and feature of corresponding relationship, and different stall grades can be found out by testing
The stall feature such as these ranges, feature and amplitude is cured in controller by corresponding vibration amplitude, logical in engine operating
The signal that vibrating sensor measures is crossed, frequency is carried out and phase property is extracted and carried out with preset stall feature in the controller
It compares, if the two has similitude, can judge that stall has occurred in low-pressure compressor by vibration signal, and then according to the frequency
Vibration amplitude amplitude corresponding with preset stall grade is compared under rate, it can be determined that stall severity, and then take
Counter-measure.It integrates the artificial neural network algorithm for having self-learning capability in the controller simultaneously, selects suitable failure sample
This progress neural metwork training realizes intelligent inference diagnostic function, and can be according to demand using test data as new study sample
This, carries out re -training to neural network, to achieve the purpose that improve diagnosis, reduce false alarm rate.
Fig. 1 shows an engine low-pressure compressor stall Typical Vibration signal time-frequency characteristics.In Fig. 1, time domain is vibrated
The horizontal axis of signal is time Time, and the longitudinal axis is Oscillation Amplitude Amplitude, the horizontal axis of the corresponding spectrum signal of vibration time-domain signal
For frequency Frequency, the longitudinal axis is Oscillation Amplitude Amplitude.As can be seen that going out in the left side of fundamental frequency from spectrum signal figure
The frequency signal of existing two characterizations stall.When stall occurs for low-pressure compressor, stall group relative rotor revolving speed has different,
And show as stall group relative rotor and circumferential movement occurs, it shows as existing with rotor fundamental frequency on rotor oscillation signal at certain
The frequency multiplication or frequency dividing of numerical relation, while having certain phase difference with fundamental frequency signal, as shown in figure 1 fundamental frequency and fractional frequency signal frequency
Shown in rate feature.The frequency and phase difference of fundamental frequency and frequency dividing generate variation with specific engine, but can be by starting in early days
Machine tests the range and feature for finding out corresponding relationship, and the corresponding vibration amplitude of different stall grades, fundamental frequency as shown in Figure 1
And the corresponding amplitude Characteristics of frequency dividing, the corresponding amplitude of fractional frequency signal are likely lower than alarming value, more than alarming value but are lower than limits value,
Or be more than limits value, three sections respectively represent, and stall does not occur, stall occurs but not serious, generation pronounced stall.By this
A little ranges, feature and amplitude are cured in engine control system, are measured in engine operating by airborne vibrating sensor
Signal, carry out frequency and phase property and extract and be compared with preset stall feature, can if the two has similitude
To judge that stall has occurred in low-pressure compressor by vibration signal, further according to vibration amplitude under the frequency and preset stall grade pair
The amplitude answered is compared, it can be determined that stall severity, and then take counter-measure.
According to established low-pressure compressor stall vibration performance, suitable artificial neural network structure is established, and select
Suitable fault sample carries out neural metwork training, is verified to the Neural Network Diagnosis conclusion using measured data,
By by verifying Artificial neural network ensemble to engine it is health management system arranged in, depending on feelings using measured data as new study sample
This, combines with original sample, carries out training again to network, has reached the effect for improving diagnosis and reducing false alarm rate
Fruit.
Aeroengine compressor monitoring method as shown in Figure 2 obtains the rotor of low-pressure compressor first
Airborne vibration signal.Then to airborne vibration signal processing, characterization stall group movement speed is extracted from the airborne vibration signal
Spend the onboard features signal related with frequency and phase lagged relative to rotor speed.Then, compare onboard features signal with
The assay features signal of stall feature database, to judge whether the low-pressure compressor handles stall conditions, judgement may include two
On the one hand whether a step occurs stall according to frequency and phase contrast judgement, on the other hand judge stall by amplitude comparison
Grade.Stall feature database is established in engine test, is tested by engine test obtain low-pressure compressor first
Vibration signal is tested caused by stall;Then from the test vibration signal extract characterization stall group movement velocity relative to turn
The assay features signal related with frequency and/or phase of rotor speed lag, establishes stall feature database;By the stall feature database
It is preset in controller.
In a preferred embodiment, in conjunction with Fig. 1, assay features signal includes stall limits value, stall alert value, according to
The amplitude of the onboard features signal is limited lower than the stall alert value, more than the stall alert value but lower than the stall
Value is more than the stall limits value, judges that stall, generation stall but not serious, hair do not occur for the low-pressure compressor respectively
Raw pronounced stall.
In a preferred embodiment, by the onboard features signal proposed during engine movements, by certainly
Learning algorithm updates the stall feature database.
Other than carrying out the judgement of stall according to airborne vibration signal, the judgement of surge can also be carried out.Related surge
This is not described in detail here for judgement, can implement in conjunction with prior art.
In one embodiment, in the case where without preset stall feature database in the controller, by aforementioned principles,
The analysis of airborne vibration signal can be judged by controller, for example, in the presence of with rotor fundamental frequency at certain numerical value relationship
Frequency signal, and have certain phase difference with fundamental frequency signal, so judge whether in stall conditions.
Fig. 3 shows an embodiment of monitoring system.As shown in figure 3, a kind of aeroengine compressor prison
Control system, including controller and airborne vibrating sensor, the controller include memory, processor and storage and the storage
On device and the program that can run on the processor, the processor execute following steps when executing described program:
Based on the monitoring of the airborne vibrating sensor, the airborne vibration signal of the rotor of low-pressure compressor is obtained;
Characterization stall group movement velocity is lagged relative to rotor speed and frequency is extracted from the airborne vibration signal
Onboard features signal related with phase;
Judge whether the low-pressure compressor handles stall conditions by the onboard features signal.
In one preferred embodiment, following steps are also executed when the processor executes described program:
The stall feature database preset from one reads assay features signal;
The assay features signal of the onboard features signal Yu the stall feature database is compared, to judge that the low pressure is calmed the anger
Whether machine handles stall conditions.
In one preferred embodiment, following steps are also executed when the processor executes described program:
The assay features signal includes stall limits value, stall alert value, according to the amplitude of the onboard features signal
Lower than the stall alert value, it is more than the stall alert value but is lower than the stall limits value, is more than the stall limits value,
Judge that stall, generation stall but not serious, generation pronounced stall do not occur for the low-pressure compressor respectively.
In one preferred embodiment, following steps are also executed when the processor executes described program: passing through institute
State airborne vibration signal judge low-pressure compressor whether surge.
In one preferred embodiment, following steps are also executed when the processor executes described program: passing through hair
The onboard features signal proposed in motivation motion process updates the stall feature database by self-learning algorithm.
Although the present invention is disclosed as above with preferred embodiment, it is not for limiting the present invention, any this field skill
Art personnel without departing from the spirit and scope of the present invention, can make possible variation and modification.Therefore, it is all without departing from
The content of technical solution of the present invention, according to the technical essence of the invention any modification to the above embodiments, equivalent variations
And modification, it each falls within the protection scope that the claims in the present invention are defined.
Claims (10)
1. aeroengine compressor monitoring method, which is characterized in that
Obtain the airborne vibration signal of the rotor of low-pressure compressor;
From the airborne vibration signal extract characterization stall group movement velocity lagged relative to rotor speed with frequency and phase
The related onboard features signal in position;
Judge whether the low-pressure compressor handles stall conditions by the onboard features signal.
2. aeroengine compressor monitoring method as described in claim 1, which is characterized in that
The test vibration signal for obtaining the rotor of low-pressure compressor is tested by engine test;
From it is described test vibration signal in extract characterization stall group movement velocity lagged relative to rotor speed with frequency and/or
The related assay features signal of phase, establishes stall feature database;
The stall feature database is preset in controller;
The assay features signal of the onboard features signal Yu the stall feature database is compared, to judge that the low-pressure compressor is
No processing stall conditions.
3. aeroengine compressor monitoring method as described in claim 1, which is characterized in that the assay features letter
Number include stall limits value, stall alert value, according to the amplitude of the onboard features signal lower than the stall alert value, be more than
The stall alert value but lower than the stall limits value, be more than the stall limits value, judge that the low pressure is calmed the anger respectively
Stall does not occur, stall occurs for machine but not serious, generation pronounced stall.
4. aeroengine compressor monitoring method as described in claim 1, which is characterized in that also by described airborne
Vibration signal judge low-pressure compressor whether surge.
5. aeroengine compressor monitoring method as claimed in claim 2, which is characterized in that pass through engine movements
The onboard features signal proposed in the process updates the stall feature database by self-learning algorithm.
6. a kind of aeroengine compressor monitoring system, including controller and airborne vibrating sensor, the controller packet
It includes memory, processor and is stored in the program that can be run on the memory and on the processor, which is characterized in that institute
It states when processor executes described program and executes following steps:
Based on the monitoring of the airborne vibrating sensor, the airborne vibration signal of the rotor of low-pressure compressor is obtained;
From the airborne vibration signal extract characterization stall group movement velocity lagged relative to rotor speed with frequency and phase
The related onboard features signal in position;
Judge whether the low-pressure compressor handles stall conditions by the onboard features signal.
7. aeroengine compressor monitoring system as claimed in claim 6, which is characterized in that the processor executes
Following steps are also executed when described program:
The stall feature database preset from one reads assay features signal;
The assay features signal of the onboard features signal Yu the stall feature database is compared, to judge that the low-pressure compressor is
No processing stall conditions.
8. aeroengine compressor monitoring system as claimed in claim 7, which is characterized in that the processor executes
Following steps are also executed when described program:
The assay features signal includes stall limits value, stall alert value, is lower than according to the amplitude of the onboard features signal
The stall alert value is more than the stall alert value but is lower than the stall limits value, is more than the stall limits value, respectively
Judge that stall, generation stall but not serious, generation pronounced stall do not occur for the low-pressure compressor.
9. aeroengine compressor monitoring system as claimed in claim 6, which is characterized in that the processor executes
Following steps are also executed when described program: by the airborne vibration signal judge low-pressure compressor whether surge.
10. aeroengine compressor monitoring system as claimed in claim 6, which is characterized in that the processor is held
Following steps are also executed when row described program: by the onboard features signal proposed during engine movements, by certainly
Learning algorithm updates the stall feature database.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810010382.4A CN110006655A (en) | 2018-01-05 | 2018-01-05 | Aeroengine compressor monitoring method and monitoring system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810010382.4A CN110006655A (en) | 2018-01-05 | 2018-01-05 | Aeroengine compressor monitoring method and monitoring system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110006655A true CN110006655A (en) | 2019-07-12 |
Family
ID=67164474
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810010382.4A Pending CN110006655A (en) | 2018-01-05 | 2018-01-05 | Aeroengine compressor monitoring method and monitoring system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110006655A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110735669A (en) * | 2019-10-08 | 2020-01-31 | 中国航发沈阳发动机研究所 | Method and device for judging rotating stall of aviation gas turbine engine |
EP4216013A1 (en) * | 2022-01-24 | 2023-07-26 | Hamilton Sundstrand Corporation | Incipient compressor surge detection using artificial intelligence |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1291123A (en) * | 1998-02-19 | 2001-04-11 | 本特利内华达有限公司 | Diagnosing and controlling rotating stall and surge in rotating machinery |
CN1514209A (en) * | 2003-08-01 | 2004-07-21 | 重庆大学 | Rotary machine failure intelligent diagnosis method and device |
CN101050712A (en) * | 2007-05-24 | 2007-10-10 | 岂兴明 | Positive control for aviation engine turbine blade-tip gap |
CN102435293A (en) * | 2011-09-22 | 2012-05-02 | 重庆长安汽车股份有限公司 | Mounting base for vibration test of high temperature part of automobile engine |
CN103528670A (en) * | 2012-06-28 | 2014-01-22 | 西门子公司 | Stall detection of wind turbine blades |
CN103635697A (en) * | 2011-06-30 | 2014-03-12 | 开利公司 | Compressor surge detection |
CN103821749A (en) * | 2014-03-05 | 2014-05-28 | 北京工业大学 | On-line diagnosis method of stall and surge of axial fan |
CN104005975A (en) * | 2014-05-20 | 2014-08-27 | 北京工业大学 | Stall and surge diagnostic method for axial fan |
CN105827219A (en) * | 2016-03-11 | 2016-08-03 | 北京航空航天大学 | Local surge denoising method based on adaptive logarithm threshold frame analysis |
CN105865793A (en) * | 2016-03-25 | 2016-08-17 | 西北工业大学 | Method for improving vibration monitoring precision of rotor aeroengine |
CN107389337A (en) * | 2017-06-13 | 2017-11-24 | 中国航发湖南动力机械研究所 | Aeroengine rotor vibration test system |
-
2018
- 2018-01-05 CN CN201810010382.4A patent/CN110006655A/en active Pending
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1291123A (en) * | 1998-02-19 | 2001-04-11 | 本特利内华达有限公司 | Diagnosing and controlling rotating stall and surge in rotating machinery |
CN1514209A (en) * | 2003-08-01 | 2004-07-21 | 重庆大学 | Rotary machine failure intelligent diagnosis method and device |
CN101050712A (en) * | 2007-05-24 | 2007-10-10 | 岂兴明 | Positive control for aviation engine turbine blade-tip gap |
CN103635697A (en) * | 2011-06-30 | 2014-03-12 | 开利公司 | Compressor surge detection |
CN102435293A (en) * | 2011-09-22 | 2012-05-02 | 重庆长安汽车股份有限公司 | Mounting base for vibration test of high temperature part of automobile engine |
CN103528670A (en) * | 2012-06-28 | 2014-01-22 | 西门子公司 | Stall detection of wind turbine blades |
CN103821749A (en) * | 2014-03-05 | 2014-05-28 | 北京工业大学 | On-line diagnosis method of stall and surge of axial fan |
CN104005975A (en) * | 2014-05-20 | 2014-08-27 | 北京工业大学 | Stall and surge diagnostic method for axial fan |
CN105827219A (en) * | 2016-03-11 | 2016-08-03 | 北京航空航天大学 | Local surge denoising method based on adaptive logarithm threshold frame analysis |
CN105865793A (en) * | 2016-03-25 | 2016-08-17 | 西北工业大学 | Method for improving vibration monitoring precision of rotor aeroengine |
CN107389337A (en) * | 2017-06-13 | 2017-11-24 | 中国航发湖南动力机械研究所 | Aeroengine rotor vibration test system |
Non-Patent Citations (3)
Title |
---|
徐展: "基于振动法的风电机组传动链状态监测与故障诊断研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
谷勇霞 等: "对旋轴流风机旋转失速实验研究", 《煤矿机械》 * |
韩靖懿: "某型涡轮风扇式发动机喘振研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110735669A (en) * | 2019-10-08 | 2020-01-31 | 中国航发沈阳发动机研究所 | Method and device for judging rotating stall of aviation gas turbine engine |
EP4216013A1 (en) * | 2022-01-24 | 2023-07-26 | Hamilton Sundstrand Corporation | Incipient compressor surge detection using artificial intelligence |
US11859626B2 (en) | 2022-01-24 | 2024-01-02 | Hamilton Sundstrand Corporation | Incipient compressor surge detection using artificial intelligence |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110131193A (en) | Aero-engine surge fault monitoring method and system | |
CN101592590B (en) | Fault indirect diagnosis technique of rotating blade | |
EP2538034B1 (en) | MFCC and CELP to detect turbine engine faults | |
Goumas et al. | Classification of washing machines vibration signals using discrete wavelet analysis for feature extraction | |
CN109033930A (en) | Mechanical equipment fault diagnosis method based on fault mechanism and statistical model online learning | |
CN107701468B (en) | A kind of online integrated monitoring of mixed-flow pump and device | |
EP1762831A1 (en) | Health monitoring of a mechanical system | |
CN104075795A (en) | Method and system for monitoring vibration state of impeller of wind generating set | |
CN109209783A (en) | A kind of method and device of the lightning damage based on noise measuring blade | |
CN106094570A (en) | A kind of aero-engine complete machine health evaluating method under variable working condition based on operating mode's switch and this distance of paddy | |
CN103616187A (en) | Fault diagnosis method based on multi-dimension information fusion | |
CN109655200A (en) | A kind of unbalanced diagnostic method of wind-driven generator group wind-wheel and system | |
CN110006655A (en) | Aeroengine compressor monitoring method and monitoring system | |
CN103375421A (en) | System and method for monitoring the health of stator vanes | |
CN102966526B (en) | Based on the compressor low frequency flow induced vibrations class method for diagnosing faults that axial vibration is analyzed | |
CN105829983B (en) | Equipment and method for the current faulted condition for detecting machine | |
CN117980707A (en) | Autonomous discrimination of operational vibration signals | |
CN109595130A (en) | A kind of fan blade icing failure prediction method and system | |
CN108843611A (en) | A kind of axial flow blower state identification method based on vibration signal combined spectrum correlation analysis | |
Dutta et al. | PROAD (Process Advisor): A health monitoring framework for centrifugal pumps | |
Hsu et al. | A comparison of residual-based methods on fault detection | |
CN110826600B (en) | Engine surge prediction method based on adaptive resonance network online incremental learning | |
CN110826587A (en) | Improved weighted support vector machine-based turboshaft engine fault detection method | |
CN102072139B (en) | Method for judging low-frequency vibrating failure of compressor quickly | |
Aravinth et al. | Air compressor fault diagnosis through vibration signals using statistical features and J48 algorithms |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190712 |