CN112749764A - Aeroengine running state classification method based on QAR data - Google Patents
Aeroengine running state classification method based on QAR data Download PDFInfo
- Publication number
- CN112749764A CN112749764A CN202110119388.7A CN202110119388A CN112749764A CN 112749764 A CN112749764 A CN 112749764A CN 202110119388 A CN202110119388 A CN 202110119388A CN 112749764 A CN112749764 A CN 112749764A
- Authority
- CN
- China
- Prior art keywords
- data
- qar
- section
- aircraft engine
- segment
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 52
- 238000013145 classification model Methods 0.000 claims abstract description 27
- 238000012549 training Methods 0.000 claims abstract description 27
- 238000003384 imaging method Methods 0.000 claims abstract description 26
- 238000012545 processing Methods 0.000 claims abstract description 24
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 20
- 238000007781 pre-processing Methods 0.000 claims abstract description 7
- 230000008569 process Effects 0.000 claims description 16
- 230000002159 abnormal effect Effects 0.000 claims description 13
- 238000012360 testing method Methods 0.000 claims description 13
- 238000005406 washing Methods 0.000 claims description 10
- 230000009194 climbing Effects 0.000 claims description 8
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 4
- 238000003672 processing method Methods 0.000 claims description 3
- 238000003745 diagnosis Methods 0.000 abstract description 4
- 230000000694 effects Effects 0.000 abstract description 4
- 230000036541 health Effects 0.000 abstract description 4
- 230000009286 beneficial effect Effects 0.000 abstract description 3
- 238000004458 analytical method Methods 0.000 abstract description 2
- 230000008859 change Effects 0.000 description 7
- 238000012423 maintenance Methods 0.000 description 6
- 238000013528 artificial neural network Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 3
- 230000007423 decrease Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computational Linguistics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Evolutionary Biology (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Testing And Monitoring For Control Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to the technical field of analysis of aero-engine running state data, in particular to a QAR data-based aero-engine running state classification method, which comprises the steps of preprocessing acquired QAR data; carrying out imaging processing on the preprocessed QAR data; putting the QAR data after the imaging processing into a convolutional neural network for training to generate an aeroengine operation state classification model; and adopting the classification model to classify the fault state of the engine with the fault. The classification method provided by the invention combines full-flight QAR data imaging processing with a convolutional neural network to obtain a classification model, and then uses the classification model to classify the data into fault states. The classification method can achieve an accurate classification effect and is beneficial to researching state identification and fault diagnosis of the aero-engine, so that the flight safety can be improved, the cost can be reduced, and the method has an important significance for health management of the aero-engine based on a data driving method.
Description
Technical Field
The invention relates to the technical field of analysis of aero-engine running state data, in particular to a QAR data-based aero-engine running state classification method.
Background
The aircraft engine is the main power source in the aircraft flight process, and the health degree and the working state of the aircraft engine directly influence the flight safety. The degradation or failure of an aircraft engine can change its operating state, which in turn can lead to changes in various parameters of the engine during operation. The change of the operation parameters is recorded in detail and truly by an airplane mark configuration component QAR (Quick Access Recorder), the change can continuously and completely reflect the actual state or failure sign signals of the airplane system in operation, and the change recording method has the advantages of easy Access, simple maintenance, large data storage capacity, cheap airborne storage equipment and strong universality. QAR data is therefore important in aircraft engine operating condition monitoring applications.
The existing method for classifying fault states based on aircraft engine simulation data can achieve high accuracy, but the simulation data may not reflect the distribution rule of real operating data, the engine data in the real operating state contains a large amount of noise, different types of parameters have strong nonlinearity and coupling relevance, and the traditional data processing and classifying method cannot achieve a good classifying effect. Meanwhile, most of the existing research on the flight data of the aero-engine selects the data of the cruise stable point, but the aircraft rarely has larger faults in the cruise steady-state flight process, so that the fault state classification of the data cannot be comprehensively and accurately carried out.
Disclosure of Invention
In order to solve the technical problem that the fault state or the running state of the aircraft engine cannot be completely and accurately classified, the invention provides a QAR data-based aircraft engine running state classification method, which comprises the following steps: s100, preprocessing the acquired QAR data; s200, carrying out imaging processing on the preprocessed QAR data; s300, putting the QAR data subjected to imaging processing into a convolutional neural network for training to generate an aeroengine operation state classification model; and S400, adopting the classification model to classify the fault state of the engine with the fault.
Based on the above technical solution, further, the preprocessing of the QAR data obtained in step S100 includes abnormal value processing and missing value padding.
Based on the above technical solution, the processing method of the abnormal value processing and the missing value filling is an average value filling method, that is, the nth number of the m-th feature is an abnormal value or a missing value and is marked as Xm(n) by the formula
Replacing abnormal values or missing values in the original data with Xm(n)。
In addition to the above technical solution, in step S200, the QAR data imaging process includes:
s210, dividing original QAR data into different operation state categories according to washing records;
s220, under the same operation state type, dividing the flight cycle data of each time into a plurality of sections according to a flight section division standard, wherein each section at least comprises one of a takeoff section, a climbing section, a cruise section, a descent section and a landing section;
s230, equally dividing the data of each section into points;
and S240, converting the data with the equidistant points into three-channel data.
On the basis of the above technical solution, further, in step S220, the division criteria of different legs are as follows:
a takeoff section: CAS > 45& ALT <2000
A climbing section: 2000< ALT <20000
And (3) a cruise section: ALT > 20000& diff (ALT) <50
A landing section: 2000< ALT <20000
Landing stage: CAS > 45& ALT <2000
Where CAS is the calculated air velocity, ALT is the fly height, and diff is the difference function.
On the basis of the technical scheme, the data of the takeoff segment and the climb segment are extracted from the QAR data which meets the requirements of the flight segment division standard and is one half of the data before the whole flight cycle, and the data of the landing segment are extracted from the QAR data which meets the requirements of the flight segment division standard and is one half of the data after the whole flight cycle.
Based on the above technical solution, further, in step S240, the data after equidistant point extraction is converted into three-channel data, including that n equidistant data points are respectively extracted from the takeoff segment and the climb segment as first channel data, 2n equidistant data points are extracted from the cruise segment as second channel data, and n equidistant data points are respectively extracted from the descent segment and the landing segment as third channel data, so that the data scale after multi-channel data conversion is the same.
On the basis of the technical scheme, the three-channel data are further set as imaging data with the row pixel number of 2n and the column pixel number of the aeroengine characteristic number recorded by the original QAR data.
On the basis of the above technical solution, further, in step S300, the process of obtaining the classification model of the operation state of the aircraft engine includes: carrying out data standardization on the QAR data subjected to imaging processing according to the following formula so as to obtain an aircraft engine operation state classification model by training standardized data through a convolutional neural network;
wherein,
on the basis of the above technical solution, further, the step S300 further includes dividing the standardized data into a training set and a test set according to a certain proportion; the training set is used for training standardized data through a convolutional neural network to obtain an aero-engine running state classification model, and the testing set is used for observing the classification accuracy of the model.
Compared with the prior art, the method for classifying the running states of the aircraft engine based on the QAR data has the following advantages that: and (3) carrying out imaging processing on QAR data in the full flight range, combining the QAR data with a convolutional neural network to obtain an aero-engine running state classification model, and carrying out fault state classification on the QAR data by using the classification model. The classification method can achieve an accurate classification effect, is beneficial to researching the state identification and fault diagnosis of the aero-engine, has important significance for the health management of the aero-engine based on the data driving method, provides possibility for the airline company to maintain the condition of the aero-engine, and reduces the maintenance cost while improving the flight safety.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a flow chart illustrating the steps of a QAR data based method for classifying the operational status of an aircraft engine according to the present invention;
FIG. 2 is an aircraft engine state data classification diagram;
FIG. 3 is a flow chart of an aircraft engine QAR data imaging process;
FIG. 4 is a flowchart of the training steps of the graphical data input convolutional neural network;
FIG. 5 is a schematic diagram of the change in model classification accuracy during the training process;
FIG. 6 is a diagram of a confusion matrix for model classification.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention provides an aeroengine running state classification method based on QAR data, which comprises the following steps: s100, preprocessing the acquired QAR data; s200, carrying out imaging processing on the preprocessed QAR data; s300, putting the QAR data subjected to imaging processing into a convolutional neural network for training to generate an aeroengine operation state classification model; and S400, adopting the classification model to classify the fault state of the engine with the fault.
In the specific implementation, the QAR data and the maintenance records of an aircraft engine are introduced, wherein each QAR data file records the change of more than 20 parameters of a complete flight cycle, including environment parameters such as the flight Altitude (ALT) and the Total Air Temperature (TAT) of the engine, performance parameters such as the High Pressure compressor Speed (N2) and the Exhaust Temperature (EGT), and control parameters such as the adjustable Stator Vane (VSV), and the maintenance records include the time for washing the engine. When the QAR data is classified, due to the frequency difference of the recorded data of the sensors at different parts of the aircraft engine and the influence of the operating environment on the sensors, the QAR data file often contains various errors, and the extraction of effective information in the QAR data is influenced by the existence of the errors. Therefore, as shown in fig. 1, it is necessary to first pre-process the QAR data, then perform imaging processing on the pre-processed data to make it better adapt to the convolutional neural network, and then input the data into the convolutional neural network for training to generate an aero-engine operating state classification model, so as to achieve the purpose of classifying the fault state of the engine with faults through the model.
The invention provides an aeroengine running state classification method based on QAR data, which is characterized in that the QAR data in a full flight segment is subjected to imaging processing and is combined with a convolutional neural network to obtain an aeroengine running state classification model, and the classification model is utilized to classify the QAR data into fault states. The classification method can achieve an accurate classification effect, is beneficial to researching the state identification and fault diagnosis of the aero-engine, has important significance for the health management of the aero-engine based on the data driving method, provides possibility for the airline company to maintain the condition of the aero-engine, and reduces the maintenance cost while improving the flight safety.
Preferably, the preprocessing of the acquired QAR data in step S100 includes outlier processing and missing value padding.
In specific implementation, abnormal values and missing values in the QAR data are processed, so that errors in data transmission can be effectively reduced, and subsequent monitoring and diagnosis are prevented from being influenced.
Preferably, the processing method of the abnormal value processing and the missing value filling is an average value filling method, that is, the nth number of the m-th feature is an abnormal value or a missing value and is marked as Xm(n) by the formula
Replacing abnormal values or missing values in the original data with Xm(n)。
In specific implementation, the abnormal value and the missing value are processed by an average value filling method, the abnormal value and the missing value are replaced by the average value of the previous value and the next value, and data are stabilized in a more effective range so as to reduce errors.
Preferably, in step S200, the QAR data imaging process includes:
s210, dividing original QAR data into different operation state categories according to washing records;
s220, under the same operation state type, dividing the flight cycle data of each time into a plurality of sections according to a flight section division standard, wherein each section at least comprises one of a takeoff section, a climbing section, a cruise section, a descent section and a landing section;
s230, equally dividing the data of each section into points;
and S240, converting the data with the equidistant points into three-channel data.
In specific implementation, as the aeroengine fault samples are fewer in the real flight process, but the service time is prolonged, the performance decline of the aeroengine can also cause the data distribution to change, and the performance decline of the engine caused by the fouling can be recovered by washing the engine, but the performance of the engine after washing is still declined to a certain extent compared with the performance of the engine after the previous washing. Therefore, different operation states of the aircraft engine can be distinguished through the washing time, and as shown in fig. 2, the original QAR data is divided into four different operation states according to five times of washing maintenance records.
Therefore, when the QAR data is subjected to the imaging processing, the original QAR data needs to be classified into different operation state categories according to the washing records, and the data of the cycle of each flight is classified into several segments according to the flight segment classification standard in the same operation state category. And then, points are taken for the data of each segment at equal intervals, so that the data volume can be reduced on the premise of ensuring that the information is not lost much, and the three channels of data are ensured to be the same in scale. And finally, converting the data after equidistant point taking into three-channel data, namely, imaging the data to be used as a sample of the neural network.
Preferably, in step S220, the division criteria of different legs are as follows:
a takeoff section: CAS > 45& ALT <2000
A climbing section: 2000< ALT <20000
And (3) a cruise section: ALT > 20000& diff (ALT) <50
A landing section: 2000< ALT <20000
Landing stage: CAS > 45& ALT <2000
Where CAS is the calculated air velocity, ALT is the fly height, and diff is the difference function.
In specific implementation, the flight phases of the aircraft engines in each flight cycle are different, and the engine operating states are different, so that the data of each flight cycle are divided into five flight segments according to the air speed and the flight altitude. The division standard is simple and easy to implement in the operation process, and excessive parameter intervention is not needed.
Preferably, the data of the takeoff segment and the climb segment are QAR data which meet the requirements of the leg division standard and are extracted from one half of the QAR data in the front of the whole flight cycle, and the data of the landing segment and the landing segment are QAR data which meet the requirements of the leg division standard and are extracted from one half of the QAR data in the rear of the whole flight cycle.
Preferably, in step S240, the data after equidistant point extraction is converted into three-channel data, including that n equidistant data points are respectively extracted from the takeoff segment and the climb segment as first channel data, 2n equidistant data points are extracted from the cruise segment as second channel data, and n equidistant data points are respectively extracted from the descent segment and the landing segment as third channel data, so that the data scale after multi-channel data conversion is the same.
In specific implementation, based on data after equidistant point taking, on one hand, because the working states of the takeoff section and the climbing section are similar, namely the aero-engine generates larger thrust, the cruise section engine is in a stable working state, and the working states of the descent section and the landing section are similar, namely the thrust is smaller, the flight stages with similar working states can be used as the same channel, and on the other hand, in order to ensure that the data scale is the same after multi-channel data conversion, the takeoff section and the climbing section respectively take out n equidistant data points as first channel data; taking 2n equidistant data points from the cruise segment as second channel data; and taking n equidistant data points from the descending segment and the landing segment respectively as third channel data. In this manner, the original QAR data is transformed into three-channel data as neural network samples, the flow chart of the transformation is shown in fig. 3.
Preferably, the three-channel data is set to be the imaging data of the aircraft engine characteristic quantity recorded by the original QAR data, wherein the number of the row pixel points is 2n, and the number of the column pixel points is the original QAR data.
In specific implementation, the three-channel data is set to be the imaging data of the aircraft engine characteristic quantity recorded by the original QAR data, the number of the row pixel points is 2n, and the number of the column pixel points is convenient for subsequent input into the convolutional neural network.
Preferably, in step S300, the process of obtaining the classification model of the operating state of the aircraft engine includes: carrying out data standardization on the QAR data subjected to imaging processing according to the following formula so as to obtain an aircraft engine operation state classification model by training standardized data through a convolutional neural network;
wherein,
in specific implementation, as shown in fig. 4, a convolutional neural network training process is performed, in which QAR data after imaging processing is used as a neural network sample for data standardization, which is used for eliminating the influence of different parameter dimensions in a machine learning process, and then the QAR data is placed into a convolutional neural network, and after training of the neural network, the high-accuracy aircraft engine operating state classification model can be obtained.
Preferably, the S300 further includes dividing the normalized data into a training set and a testing set according to a certain ratio; the training set is used for training standardized data through a convolutional neural network to obtain an aero-engine running state classification model, and the testing set is used for observing the classification accuracy of the model.
In particular, the normalized data may be divided into a training set and a test set according to a certain ratio, wherein the training set has more data than the test set. And putting the data of the training set into a convolutional neural network for training to obtain an aero-engine running state classification model, and finally testing the accuracy of model classification by using the test set. By this method step, the model can be well checked. As an implementation mode, the data of the training set and the test set are divided according to the ratio of 3:1, and the test set is input into the model, as shown in fig. 5, it is shown that the accuracy of classification of the test set is continuously increased in the neural network training process, and the final classification accuracy can reach more than 98%; as shown in fig. 6, the confusion of the classification of the model between different operating states is shown, and it can be found that the classification accuracy of the model for different operating states is very good. Therefore, a good classification model of the operating state of the aircraft engine can be obtained by the method provided by the invention, the fault state or the operating state of the aircraft engine can be well classified, and high classification accuracy means that the fault can be accurately positioned, so that the sudden fault of the engine can be effectively reduced.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. An aeroengine operating state classification method based on QAR data is characterized by comprising the following steps:
s100, preprocessing the acquired QAR data;
s200, carrying out imaging processing on the preprocessed QAR data;
s300, putting the QAR data subjected to imaging processing into a convolutional neural network for training to generate an aeroengine operation state classification model;
and S400, adopting the classification model to classify the fault state of the engine with the fault.
2. The QAR data-based aircraft engine operating condition classification method according to claim 1, wherein: the preprocessing of the QAR data acquired in step S100 includes outlier processing and missing value padding.
3. The QAR data-based aircraft engine operating condition classification method according to claim 2, wherein the QAR data is based on a relationship between the operating conditions of the aircraft engine and the operating conditions of the aircraft engineCharacterized in that: the processing method of abnormal value processing and missing value filling is an average value filling method, namely the nth number of the m-th characteristic is an abnormal value or a missing value and is marked as Xm(n) by the formula
Replacing abnormal values or missing values in the original data with Xm(n)。
4. The QAR data-based aircraft engine operating condition classification method according to claim 1, wherein: in step S200, the QAR data imaging process includes:
s210, dividing original QAR data into different operation state categories according to washing records;
s220, under the same operation state type, dividing the flight cycle data of each time into a plurality of sections according to a flight section division standard, wherein each section at least comprises one of a takeoff section, a climbing section, a cruise section, a descent section and a landing section;
s230, equally dividing the data of each section into points;
and S240, converting the data with the equidistant points into three-channel data.
5. The QAR data-based aircraft engine operating condition classification method according to claim 4, wherein: in step S220, the division criteria for different legs are as follows:
a takeoff section: CAS > 45& ALT <2000
A climbing section: 2000< ALT <20000
And (3) a cruise section: ALT > 20000& diff (ALT) <50
A landing section: 2000< ALT <20000
Landing stage: CAS > 45& ALT <2000
Where CAS is the calculated air velocity, ALT is the fly height, and diff is the difference function.
6. The QAR data-based aircraft engine operating condition classification method according to claim 5, wherein: the data of the takeoff segment and the climb segment are extracted from QAR data which meet the requirements of the flight segment division standard and are one half of the data in front of the whole flight cycle, and the data of the landing segment are extracted from QAR data which meet the requirements of the flight segment division standard and are one half of the data in back of the whole flight cycle.
7. The QAR data-based aircraft engine operating condition classification method according to claim 4, wherein: in step S240, the data after equidistant point extraction is converted into three-channel data, including taking n equidistant data points from the takeoff segment and the climb segment as first channel data, taking 2n equidistant data points from the cruise segment as second channel data, and taking n equidistant data points from the descent segment and the landing segment as third channel data, so that the data scale after multi-channel data conversion is the same.
8. The QAR data-based aircraft engine operating condition classification method according to claim 7, wherein: and setting the three-channel data as imaging data with the row pixel number of 2n and the column pixel number of the aeroengine characteristic number recorded by the original QAR data.
9. The QAR data-based aircraft engine operating condition classification method according to any one of claims 1 to 8, wherein: in step S300, the process of obtaining the classification model of the operating state of the aircraft engine includes: carrying out data standardization on the QAR data subjected to imaging processing according to the following formula so as to obtain an aircraft engine operation state classification model by training standardized data through a convolutional neural network;
wherein,
10. the QAR data-based aircraft engine operating condition classification method according to claim 9, wherein: the S300 further comprises dividing the standardized data into a training set and a testing set according to a certain proportion; the training set is used for training standardized data through a convolutional neural network to obtain an aero-engine running state classification model, and the testing set is used for observing the classification accuracy of the model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110119388.7A CN112749764B (en) | 2021-01-28 | 2021-01-28 | Aeroengine running state classification method based on QAR data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110119388.7A CN112749764B (en) | 2021-01-28 | 2021-01-28 | Aeroengine running state classification method based on QAR data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112749764A true CN112749764A (en) | 2021-05-04 |
| CN112749764B CN112749764B (en) | 2022-09-13 |
Family
ID=75653284
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110119388.7A Active CN112749764B (en) | 2021-01-28 | 2021-01-28 | Aeroengine running state classification method based on QAR data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112749764B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113850931A (en) * | 2021-11-29 | 2021-12-28 | 武汉大学 | Flight feature extraction method for flight abnormity |
| WO2024045246A1 (en) * | 2022-08-30 | 2024-03-07 | 大连理工大学 | Spike echo state network model for aero engine fault prediction |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120158220A1 (en) * | 2010-12-20 | 2012-06-21 | Selex Systemi Integrati S.P.A. | Fast vertical trajectory prediction method for air traffic management, and relevant atm system |
| CN106503746A (en) * | 2016-11-03 | 2017-03-15 | 哈尔滨工业大学 | A kind of Fault Diagnosis of Aeroengines method based on offset of performance amount |
| CN109115501A (en) * | 2018-07-12 | 2019-01-01 | 哈尔滨工业大学（威海） | A kind of Civil Aviation Engine Gas path fault diagnosis method based on CNN and SVM |
| US20190122360A1 (en) * | 2017-10-24 | 2019-04-25 | General Electric Company | Deep convolutional neural network with self-transfer learning |
| CN110633790A (en) * | 2019-09-19 | 2019-12-31 | 郑州大学 | Method and system for measuring residual oil quantity of airplane oil tank based on convolutional neural network |
| CN111259532A (en) * | 2020-01-13 | 2020-06-09 | 西北工业大学 | Fault diagnosis method of aeroengine control system sensor based on 3DCNN-JTFA |
| CN111368885A (en) * | 2020-02-24 | 2020-07-03 | 大连理工大学 | Aero-engine gas circuit fault diagnosis method based on deep learning and information fusion |
| CN111598161A (en) * | 2020-05-14 | 2020-08-28 | 哈尔滨工业大学（威海） | Engine gas circuit state diagnosis system based on CNN transfer learning |
| CN112257152A (en) * | 2020-10-20 | 2021-01-22 | 南京航空航天大学 | Civil aircraft flight phase identification method based on airborne data |
-
2021
- 2021-01-28 CN CN202110119388.7A patent/CN112749764B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120158220A1 (en) * | 2010-12-20 | 2012-06-21 | Selex Systemi Integrati S.P.A. | Fast vertical trajectory prediction method for air traffic management, and relevant atm system |
| CN106503746A (en) * | 2016-11-03 | 2017-03-15 | 哈尔滨工业大学 | A kind of Fault Diagnosis of Aeroengines method based on offset of performance amount |
| US20190122360A1 (en) * | 2017-10-24 | 2019-04-25 | General Electric Company | Deep convolutional neural network with self-transfer learning |
| CN109115501A (en) * | 2018-07-12 | 2019-01-01 | 哈尔滨工业大学（威海） | A kind of Civil Aviation Engine Gas path fault diagnosis method based on CNN and SVM |
| CN110633790A (en) * | 2019-09-19 | 2019-12-31 | 郑州大学 | Method and system for measuring residual oil quantity of airplane oil tank based on convolutional neural network |
| CN111259532A (en) * | 2020-01-13 | 2020-06-09 | 西北工业大学 | Fault diagnosis method of aeroengine control system sensor based on 3DCNN-JTFA |
| CN111368885A (en) * | 2020-02-24 | 2020-07-03 | 大连理工大学 | Aero-engine gas circuit fault diagnosis method based on deep learning and information fusion |
| CN111598161A (en) * | 2020-05-14 | 2020-08-28 | 哈尔滨工业大学（威海） | Engine gas circuit state diagnosis system based on CNN transfer learning |
| CN112257152A (en) * | 2020-10-20 | 2021-01-22 | 南京航空航天大学 | Civil aircraft flight phase identification method based on airborne data |
Non-Patent Citations (2)
| Title |
|---|
| 李鼎哲 等: "基于随机森林的航空发动机工作状态识别", 《空军工程大学学报》 * |
| 王奕惟 等: "基于全航段QAR数据和卷积神经网络的航空发动机状态辨识", 《航空动力学报》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113850931A (en) * | 2021-11-29 | 2021-12-28 | 武汉大学 | Flight feature extraction method for flight abnormity |
| WO2024045246A1 (en) * | 2022-08-30 | 2024-03-07 | 大连理工大学 | Spike echo state network model for aero engine fault prediction |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112749764B (en) | 2022-09-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113053171B (en) | Civil aircraft system risk early warning method and system | |
| US20230358638A1 (en) | Aero-engine bearing fault diagnosis method based on variational mode decomposition and residual network | |
| CN112749764B (en) | Aeroengine running state classification method based on QAR data | |
| US20180297718A1 (en) | Methods and apparatus to monitor health information of a turbine engine | |
| US9818242B2 (en) | Gas turbine engine anomaly detections and fault identifications | |
| US7552005B2 (en) | Method for fault diagnosis of a turbine engine | |
| US7769507B2 (en) | System for gas turbine health monitoring data fusion | |
| US6502085B1 (en) | Methods and systems for estimating engine faults | |
| CN111639467A (en) | Aero-engine service life prediction method based on long-term and short-term memory network | |
| CN111932102B (en) | Civil aircraft system risk early warning method based on dynamic control diagram | |
| CN110987439B (en) | Aeroengine fault prediction method based on Logitics regression and Xgboost model | |
| CN108304886A (en) | Aeroengine Performance Monitoring method | |
| CN112381965A (en) | Aeroengine health state identification system and method based on data mining | |
| CN114969645A (en) | Statistical distribution model-based aircraft engine state monitoring and evaluation method | |
| CN116028865A (en) | Aeroengine fault diagnosis method based on feature amplification | |
| CN112069738A (en) | Method and system for predicting residual life of electric steering engine based on DBN and multi-layer fuzzy LSTM | |
| EP3742359B1 (en) | Systems and methods for auxiliary power unit health indicator computation | |
| CN111046331A (en) | Health monitoring method based on signal abnormity | |
| DE102019214653A1 (en) | Training of machine learning models for data-driven decision-making | |
| CN116521406A (en) | Method for detecting anomaly of non-overrun flight parameter data of aero-engine based on residual gate GRU-VAE model | |
| CN114372494B (en) | Aviation turboprop engine gas circuit fault diagnosis method based on attention mechanism | |
| CN113960989A (en) | Intelligent four-rotor unmanned aerial vehicle fault diagnosis method based on convolutional neural network | |
| RU2800105C2 (en) | Computational environment for monitoring aircraft engines | |
| CN111209683A (en) | Method for constructing recognition model of working state of aircraft engine, model and recognition method | |
| DE102019214665A1 (en) | Training of a machine learning model for data-driven decision-making |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |