CN112800540A - Aeroengine load spectrum task segment modeling method based on Gaussian process regression - Google Patents
Aeroengine load spectrum task segment modeling method based on Gaussian process regression Download PDFInfo
- Publication number
- CN112800540A CN112800540A CN202110102020.XA CN202110102020A CN112800540A CN 112800540 A CN112800540 A CN 112800540A CN 202110102020 A CN202110102020 A CN 202110102020A CN 112800540 A CN112800540 A CN 112800540A
- Authority
- CN
- China
- Prior art keywords
- sample set
- task segment
- task
- value
- gaussian process
- 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 82
- 238000001228 spectrum Methods 0.000 title claims abstract description 76
- 238000012549 training Methods 0.000 claims abstract description 54
- 238000012360 testing method Methods 0.000 claims abstract description 37
- 238000005259 measurement Methods 0.000 claims abstract description 11
- 238000004458 analytical method Methods 0.000 claims abstract description 6
- 238000007781 pre-processing Methods 0.000 claims abstract description 4
- 238000010606 normalization Methods 0.000 claims description 5
- 238000010835 comparative analysis Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 241000764238 Isis Species 0.000 claims description 2
- 238000005457 optimization Methods 0.000 claims description 2
- 238000004088 simulation Methods 0.000 description 13
- 238000011160 research Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000001174 ascending effect Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000005484 gravity Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005094 computer simulation Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/15—Vehicle, aircraft or watercraft design
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/08—Probabilistic or stochastic CAD
Abstract
The invention discloses an aeroengine load spectrum task segment modeling method based on Gaussian process regression, which comprises the following steps: (1) extracting task segment data from an original actual measurement spectrum of the aircraft engine to form a task segment database; (2) preprocessing the extracted task segment; (3) establishing a training sample set and a testing sample set according to a task segment database; (4) carrying out model training by adopting a training sample set, and establishing a Gaussian process regression model of an aeroengine load spectrum task segment; (5) inputting a training sample set by adopting the model constructed in the step (4) to obtain a prediction result of the training set; (6) inputting the test sample set by adopting the model constructed in the step (4) to obtain a prediction result of the test set; (7) and calculating the error between the predicted value and the actually measured value of the load spectrum task segment, and comparing, analyzing and verifying the accuracy of the Gaussian process regression model. The invention provides a foundation for the strength analysis and the load spectrum prediction and compilation of the engine.
Description
Technical Field
The invention relates to the technical field of aeroengine load spectrums, in particular to an aeroengine load spectrum task segment modeling method based on Gaussian process regression.
Background
The aeroengine technology is a key technology of the prior development of the military and the strong country in the world and the high monopoly and strict blockade, and is an important mark for national equipment military level, scientific and technological strength and comprehensive national strength. The aeroengine load spectrum is the basis of stress analysis, structural design criteria, durability test and service life analysis of parts and complete machines of the engine. The aeroengine load spectrum task segment is the minimum basic unit of the aeroengine load spectrum and is the most specific load state reflection when the aeroengine executes various tasks. The modeling of the task segment is the foundation of the simulation modeling of the engine load spectrum task section and is also the important foundation of the simulation, the compilation and the design of the engine complete machine load spectrum. Therefore, the modeling method for researching the mission segment of the aeroengine load spectrum has important significance. Because the aeroengine technology is blocked, relevant research data is not disclosed abroad, and the current domestic aeroengine load spectrum modeling method mainly comprises the following steps:
the method comprises the steps of performing statistical analysis on a gravity center normal overload spectrum of an engine by using an engine load spectrum model and simulation research related to operation, describing arrival time and duration of each level of load of the load spectrum by using a Poisson random distribution process, obtaining the passing times and duration of each level of load by calculating the distribution characteristics of the duration and the arrival time of each level of load, respectively fitting the relation among distribution parameters, the passing times, the duration and each level of load, establishing a mathematical model for describing the load, and simulating the gravity center normal overload spectrum of the engine by using sine waves and half sine waves in a grading manner. The modeling method takes the whole load spectrum task section as a unit for modeling, but the concept of a task section is not provided in the model, the comparison and display error is larger through counting the rain flow counting results before and after modeling, the influence of a load sequence is not considered in the modeling process, and the actual change characteristics of the load cannot be accurately reflected by adopting sine wave simulation.
The literature, "simulation of maneuvering flight load spectrum based on task segment database" takes task segments as a modeling unit, describes peak values of the task segments of the load spectrum by adopting three-parameter Weibull distribution, describes arrival time and duration time of the task segments by Poisson distribution, and acquires numerical information of the peak values, the arrival time and the duration time of the task segments by random number extraction; and analyzing and counting the correlation between the duration and the arrival time and the correlation between the duration and the peak value, and simulating by adopting the spectrum type of the original spectrum task segment on the premise of ensuring the consistency of the correlation. In the modeling method, the task segments are defined as the load segments with obviously changed load characteristics, the task segments have no clear practical significance, the modeling method still takes the load spectrum task section as a modeling unit actually, in addition, the simulation random load spectrum is obtained by randomly combining all the simulation task segments in the modeling process, and the modeling result also loses load sequence information, so that the modeling precision is not high.
The literature 'research on the comprehensive task spectrum compilation method of the aero-engine using the correlation' also adopts a random process theory to respectively model the maneuvering load spectrum and the aerodynamic load spectrum, the division of task segments in the literature also adopts a method of extracting random numbers from a random process model according to the mathematical characteristics of loads, triangular waves with different peak numbers and peak sizes are adopted for the maneuvering load spectrum task segment, triangular waves and trapezoidal waves are adopted for the aerodynamic load spectrum task segment to simulate, and finally the simulation results of the task segments are randomly combined to obtain the modeling result of the complete machine load spectrum. However, the definition of the task segment in the modeling method also has no practical significance, the random combination of the simulation task segments also causes the load spectrum modeling result to lose load sequence information, and the simulation of the task segment by adopting standard waveforms such as triangular waves or trapezoidal waves and the like can not accurately reflect the actual change characteristics of the load, so that the precision of the modeling result is not high.
Patent 112115787a, "method for dividing task segments of a load spectrum of an aircraft engine based on actual flight actions," proposes to define task segments as load segments with load characteristics having similar variation characteristics when the aircraft engine executes various types of complete actual flight actions, and the definition of the task segments has meanings related to actual operations and actual flight actions. However, the types of the task segments of the aeroengine load spectrum obtained by division are various, the characteristics of the different types of the task segments are different, the similar task segments are similar in shape but different, the load characteristics are disordered, and a good solution for accurately modeling the task segments cannot be found up to now.
Therefore, it is necessary to adopt the aero-engine load spectrum task segment with practical significance as a modeling unit, and a simple and effective aero-engine load spectrum task segment modeling method capable of accurately reflecting the load mathematical characteristics, the change characteristics and the sequence characteristics of the load spectrum task segment and overcoming the characteristic differences among similar task segments is provided.
Disclosure of Invention
The invention aims to solve the technical problem of providing a Gaussian process regression-based modeling method for a load spectrum task segment of an aeroengine, so as to solve the problem that accurate and efficient modeling cannot be performed due to various task segments and disordered features at present, and provide a basis for strength analysis of the engine and prediction and compilation of a load spectrum.
In order to solve the technical problem, the invention provides an aeroengine load spectrum task segment modeling method based on Gaussian process regression, which comprises the following steps:
(1) extracting task segment data from an original actual measurement spectrum of the aircraft engine to form a task segment database;
(2) preprocessing the extracted task segment, standardizing the length of the task segment and normalizing the numerical value of the task segment;
(3) establishing a training sample set and a testing sample set according to a task segment database;
(4) carrying out model training by adopting a training sample set, and establishing a Gaussian process regression model of an aeroengine load spectrum task segment;
(5) inputting a training sample set by adopting the model constructed in the step (4) to obtain a prediction result of the training set;
(6) inputting the test sample set by adopting the model constructed in the step (4) to obtain a prediction result of the test set;
(7) and calculating the error between the predicted value and the actually measured value of the load spectrum task segment, and comparing, analyzing and verifying the accuracy of the Gaussian process regression model.
Preferably, in the step (1), the task segment data is extracted from the original actual measurement spectrum of the aircraft engine, and the task segment database is formed by the following specific steps: according to the original load spectrum data of the aircraft engine, a large number of similar task segment data are extracted from different types of task profiles, and a task segment database with the total number of n task segments is established.
Preferably, in the step (2), the extracted task segments are preprocessed, and the length normalization and the numerical value normalization are specifically as follows: the length x value and the value y value of each extracted task segment are different, so that each extracted task segment is preprocessed before modeling, dimensionless processing is carried out on the length x value and the value y value, all the task segment length x values are processed into the same length according to proportional standardization, the specific value y value of each task segment is linearly normalized, and the actual measurement value is scaled in equal proportion, so that the result is mapped to the range of [0,1 ].
Preferably, in the step (3), the establishing of the training sample set and the testing sample set according to the task segment database specifically includes: randomly dividing n samples in the task segment database preprocessed according to the step (2) into two types, and respectively establishing a training sample set A { (x)i,yi) 1,2, … …, a and test sample set B { (x)j,yj) 1,2, … …, b, where a is the number of samples in the training sample set, b is the number of samples in the test sample set, and a + b is n.
Preferably, in the step (4), model training is performed by using a training sample set, and the establishing of the gaussian process regression model of the aero-engine load spectrum task segment specifically comprises: the input variable in the training sample set is xiThe corresponding output variable is yiAnd the target output value y is usually a function of the actual outputThe quantity f (x) has a certain error which is an independent random variable, the obedient mean is 0, and the variance is sigman 2Is calculated, thus it is possible to obtain:
selecting a square exponential covariance function as a covariance function in the established Gaussian process regression model, namely:
where l is a scale of the variance,is the signal variance. Thus, the hyper-parameters of the model are combined asBy inputting the data of the training sample set, the specific numerical values of the hyper-parameters can be obtained through optimization, so that the condition distribution of the predicted values is obtained, and a Gaussian process regression model of the task segment is established.
Preferably, in the step (5), the model constructed in the step (4) is adopted, and a training sample set is input, so that the prediction result of the training set is specifically: and (4) inputting the task segment length data x value of the training sample set A into the Gaussian process regression model obtained in the step (4) to obtain a predicted value of each task segment of the training sample set, namely the model of the task segment of the training sample set.
Preferably, in the step (6), the model constructed in the step (4) is adopted, and the test sample set is input, so that the prediction result of the test set is specifically: and (4) inputting the task segment length data x value of the test sample set B into the Gaussian process regression model obtained in the step (4) to obtain a predicted value of the test sample set, namely the model of the task segment of the test sample set.
Preferably, in the step (7), the error between the predicted value and the actual measurement value of the load spectrum task segment is calculated, and the accuracy of the gaussian process regression model is verified through comparative analysis specifically as follows: and (4) respectively carrying out error comparison analysis on the predicted values of the training sample set and the test sample set obtained in the steps (5) and (6) and the original actual measurement value y value of the load spectrum task segment, and verifying the accuracy of the regression model of the Gaussian process provided by the invention.
The invention has the beneficial effects that: (1) the method solves the problem of low modeling precision caused by modeling simulation of the task segment by adopting standard waveforms such as triangular waves, trapezoidal waves or sine waves and the like, can more accurately describe the characteristic rule of the task segment, and has higher modeling precision; (2) the invention combines the load spectrum task segment related to the actual flight action, and can establish a complete machine load spectrum simulation model with actual load sequence information based on the task segment simulation model obtained by the invention, and the modeling result is closer to the load condition of the actual use of the engine; (3) the method is suitable for modeling of various task segments, has strong universality, is simple and efficient in modeling method, can overcome characteristic differences among the task segments of the same type, has accurate modeling results, and can lay an important foundation for statistics, compilation and prediction of engine load spectrums.
Drawings
FIG. 1 is a schematic flow chart of the method of the present invention.
FIG. 2 is a diagram showing the preprocessing result of the part 'descending 1000 meters and turning 180 degrees, then ascending 1000 meters and turning 180 degrees' of the task section according to the invention.
FIG. 3 is a schematic diagram of the prediction result of the training sample based on the Gaussian process regression according to the present invention.
FIG. 4 is a schematic diagram of the prediction results of the test samples based on Gaussian process regression according to the present invention.
Detailed Description
As shown in fig. 1, a method for modeling a mission segment of an aircraft engine load spectrum based on gaussian process regression includes the following steps:
(1) according to original load spectrum data of a certain type of aeroengine, extracting a large amount of class task segment data of 'descending 1000 meters and turning 180 degrees and then ascending 1000 meters and turning 180 degrees' from different types of task profiles, and establishing a task segment database with the total number of task segments being 70;
(2) the extracted task segments are preprocessed before modeling, and the length (x value) and the value (y value) of each extracted task segment are subjected to dimensionless processing due to the fact that the length (x value) and the value (y value) of each extracted task segment are different. Standardizing all task segment lengths (x values) according to a proportion to be the same length, performing linear normalization on specific numerical values (y values) of each task segment, scaling the actual measurement numerical values in an equal proportion to enable the result to be mapped to the range of [0,1], and enabling the preprocessed part to descend by 1000 meters and turn 180 degrees, then ascend by 1000 meters and turn 180 degrees, wherein the task segment is shown in figure 2;
(3) randomly dividing 70 task segment samples of the task segment database preprocessed according to the step (2) into two types, and respectively establishing a training sample set A { (x)i,yi) 1,2, …,50 |, and test sample set B { (x)j,yj)|j=1,2,…,20};
(4) Model training is carried out by adopting a training sample set, and the input variable in the training sample set is xiThe corresponding output variable is yiThe target output value y usually has a certain error with the actual output variable f (x), the error is an independent random variable, the obedient mean value is 0, and the variance isIs calculated, thus it is possible to obtain:
selecting a square exponential covariance function as a covariance function in the established Gaussian process regression model, namely:
where l is a scale of the variance,is the signal variance. Thus, the hyper-parameters of the model are combined asBy inputting training sample set data, specific values of each hyper-parameter are obtained as log (l) 3.4659 and log (sigma)f)=-0.9198,log(σn) -3.4717, thereby obtaining a conditional distribution of each predicted value, thereby establishing a gaussian process regression model of the task segment.
(5) Inputting the task segment length data (x value) of the training sample set A into the Gaussian process regression model obtained in the step (4) to obtain a predicted value { f) of the training sample set*(xi) 1, …,50, that is, a model of a training sample set task segment, wherein the prediction result of the training sample set is shown in fig. 3, a black "+" point in the graph is a training sample data point, and a black line is a training sample prediction value obtained according to a gaussian process regression model;
(6) inputting the task segment length data (x value) of the test sample set B into the Gaussian process regression model obtained in the step (4) to obtain a predicted value { f) of the test sample set*(xj) 1, …,20, that is, a model of a task segment of the test sample set, where the prediction result of the test sample set is shown in fig. 4, a black "o" point in the graph is a test sample data point, and a black line is a test sample prediction value obtained according to a gaussian process regression model;
(7) and (3) respectively carrying out error calculation on the training sample set and the test sample set predicted values obtained in the steps (5) and (6) and the original actual measurement values (y values) of the load spectrum task segment by adopting an average absolute error MAE and a mean square error MSE:
the errors of the modeling results obtained by calculation are shown in table 1:
TABLE 1 aeroengine load spectrum task segment modeling error calculation results
Through comparative analysis, the Gaussian process regression model provided by the invention has higher accuracy.
Through the embodiment, the method realizes the modeling of the aeroengine load spectrum task segment based on the Gaussian process regression, and ensures the accuracy of the modeling result. The modeling method is simple and feasible, can accurately establish the simulation model of the mission segment of the load spectrum of the aero-engine, and has important significance for compilation and prediction research of the load spectrum of the whole aero-engine.
Claims (8)
1. A method for modeling an aeroengine load spectrum task segment based on Gaussian process regression is characterized by comprising the following steps:
(1) extracting task segment data from an original actual measurement spectrum of the aircraft engine to form a task segment database;
(2) preprocessing the extracted task segment, standardizing the length of the task segment and normalizing the numerical value of the task segment;
(3) establishing a training sample set and a testing sample set according to a task segment database;
(4) carrying out model training by adopting a training sample set, and establishing a Gaussian process regression model of an aeroengine load spectrum task segment;
(5) inputting a training sample set by adopting the model constructed in the step (4) to obtain a prediction result of the training set;
(6) inputting the test sample set by adopting the model constructed in the step (4) to obtain a prediction result of the test set;
(7) and calculating the error between the predicted value and the actually measured value of the load spectrum task segment, and comparing, analyzing and verifying the accuracy of the Gaussian process regression model.
2. The method for modeling the mission segment of the aeroengine load spectrum based on the gaussian process regression as claimed in claim 1, wherein in the step (1), mission segment data is extracted from the original measured spectrum of the aeroengine, and a mission segment database is formed by: according to the original load spectrum data of the aircraft engine, a large number of similar task segment data are extracted from different types of task profiles, and a task segment database with the total number of n task segments is established.
3. The method for modeling the aero engine load spectrum task segment based on gaussian process regression as claimed in claim 1, wherein in the step (2), the extracted task segment is preprocessed, and the length normalization and the numerical normalization are specifically as follows: the length x value and the value y value of each extracted task segment are different, so that each extracted task segment is preprocessed before modeling, dimensionless processing is carried out on the length x value and the value y value, all the task segment length x values are processed into the same length according to proportional standardization, the specific value y value of each task segment is linearly normalized, and the actual measurement value is scaled in equal proportion, so that the result is mapped to the range of [0,1 ].
4. The method for modeling the mission segment of the aeroengine load spectrum based on the gaussian process regression as claimed in claim 1, wherein in the step (3), the establishing of the training sample set and the testing sample set according to the mission segment database specifically comprises: randomly dividing n samples in the task segment database preprocessed according to the step (2) into two types, and respectively establishing a training sample set A { (x)i,yi) 1,2, … …, a and test sample set B { (x)j,yj) 1,2, … …, b, where a is the number of samples in the training sample set, b is the number of samples in the test sample set, and a + b is n.
5. The method for modeling the aero-engine load spectrum task segment based on gaussian process regression as claimed in claim 1, wherein in the step (4), model training is performed by using a training sample set, and the gaussian process regression model for establishing the aero-engine load spectrum task segment specifically comprises: the input variable in the training sample set is xiThe corresponding output variable is yiAnd the target output value y is generally related to the actual output variable(x) has a certain error, the error is an independent random variable, the obedient mean value is 0, and the variance isIs calculated, thus it is possible to obtain:
selecting a square exponential covariance function as a covariance function in the established Gaussian process regression model, namely:
where l is a scale of the variance,is the signal variance. Thus, the hyper-parameters of the model are combined asBy inputting the data of the training sample set, the specific numerical values of the hyper-parameters can be obtained through optimization, so that the condition distribution of the predicted values is obtained, and a Gaussian process regression model of the task segment is established.
6. The method for modeling the aero-engine load spectrum task segment based on gaussian process regression as claimed in claim 1, wherein in the step (5), the model constructed in the step (4) is adopted, a training sample set is input, and the prediction result of the training set is specifically: and (4) inputting the task segment length data x value of the training sample set A into the Gaussian process regression model obtained in the step (4) to obtain a predicted value of each task segment of the training sample set, namely the model of the task segment of the training sample set.
7. The method for modeling the aero engine load spectrum task segment based on gaussian process regression as claimed in claim 1, wherein in the step (6), the model constructed in the step (4) is adopted, the test sample set is input, and the prediction result of the test set is specifically: and (4) inputting the task segment length data x value of the test sample set B into the Gaussian process regression model obtained in the step (4) to obtain a predicted value of the test sample set, namely the model of the task segment of the test sample set.
8. The method for modeling the load spectrum task segment of the aircraft engine based on gaussian process regression as claimed in claim 1, wherein in the step (7), the error between the predicted value and the measured value of the load spectrum task segment is calculated, and the accuracy of the gaussian process regression model is verified through comparative analysis specifically as follows: and (4) respectively carrying out error comparison analysis on the predicted values of the training sample set and the test sample set obtained in the steps (5) and (6) and the original actual measurement value y value of the load spectrum task segment, and verifying the accuracy of the regression model of the Gaussian process provided by the invention.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110102020.XA CN112800540B (en) | 2021-01-26 | 2021-01-26 | Aircraft engine load spectrum task segment modeling method based on Gaussian process regression |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110102020.XA CN112800540B (en) | 2021-01-26 | 2021-01-26 | Aircraft engine load spectrum task segment modeling method based on Gaussian process regression |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112800540A true CN112800540A (en) | 2021-05-14 |
CN112800540B CN112800540B (en) | 2023-12-19 |
Family
ID=75811749
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110102020.XA Active CN112800540B (en) | 2021-01-26 | 2021-01-26 | Aircraft engine load spectrum task segment modeling method based on Gaussian process regression |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112800540B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114459644A (en) * | 2021-12-30 | 2022-05-10 | 南京航空航天大学 | Undercarriage drop load identification method based on optical fiber strain response and Gaussian process |
CN116227148A (en) * | 2022-12-31 | 2023-06-06 | 中国航发沈阳发动机研究所 | Method for constructing maneuvering overload spectrum of aeroengine |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20000046441A (en) * | 1998-12-31 | 2000-07-25 | 추호석 | Method for analyzing load/stress for maintaining life span of fuselage of airplane |
US20170293712A1 (en) * | 2016-04-11 | 2017-10-12 | Airbus Helicopters Deutschland GmbH | Probabilistic load and damage modeling for fatigue life management |
CN108717474A (en) * | 2018-04-08 | 2018-10-30 | 南京航空航天大学 | It is a kind of to compose preparation method with using relevant aero-engine comprehensive task |
CN110516288A (en) * | 2019-07-10 | 2019-11-29 | 南京航空航天大学 | It is a kind of with the relevant aero-engine loading spectrum Mixture Distribution Model method for building up of use |
CN112115787A (en) * | 2020-08-14 | 2020-12-22 | 南京航空航天大学 | Aero-engine load spectrum task segment dividing method based on actual flight action |
-
2021
- 2021-01-26 CN CN202110102020.XA patent/CN112800540B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20000046441A (en) * | 1998-12-31 | 2000-07-25 | 추호석 | Method for analyzing load/stress for maintaining life span of fuselage of airplane |
US20170293712A1 (en) * | 2016-04-11 | 2017-10-12 | Airbus Helicopters Deutschland GmbH | Probabilistic load and damage modeling for fatigue life management |
CN108717474A (en) * | 2018-04-08 | 2018-10-30 | 南京航空航天大学 | It is a kind of to compose preparation method with using relevant aero-engine comprehensive task |
CN110516288A (en) * | 2019-07-10 | 2019-11-29 | 南京航空航天大学 | It is a kind of with the relevant aero-engine loading spectrum Mixture Distribution Model method for building up of use |
CN112115787A (en) * | 2020-08-14 | 2020-12-22 | 南京航空航天大学 | Aero-engine load spectrum task segment dividing method based on actual flight action |
Non-Patent Citations (1)
Title |
---|
宋迎东, 孙志刚: "操作相关的发动机载荷谱模型与仿真研究", 航空动力学报, no. 06 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114459644A (en) * | 2021-12-30 | 2022-05-10 | 南京航空航天大学 | Undercarriage drop load identification method based on optical fiber strain response and Gaussian process |
CN116227148A (en) * | 2022-12-31 | 2023-06-06 | 中国航发沈阳发动机研究所 | Method for constructing maneuvering overload spectrum of aeroengine |
CN116227148B (en) * | 2022-12-31 | 2024-02-02 | 中国航发沈阳发动机研究所 | Method for constructing maneuvering overload spectrum of aeroengine |
Also Published As
Publication number | Publication date |
---|---|
CN112800540B (en) | 2023-12-19 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111104981B (en) | Hydrological prediction precision evaluation method and system based on machine learning | |
US20200148395A1 (en) | Method for prediction of key performance parameters of aero-engine in transition condition | |
CN112800540B (en) | Aircraft engine load spectrum task segment modeling method based on Gaussian process regression | |
CN104820771B (en) | A kind of aerospace engineering manufacture maturity grade determines method | |
CN110059845B (en) | Metering device clock error trend prediction method based on time sequence evolution gene model | |
CN112800541A (en) | Aero-engine load spectrum task segment modeling method based on support vector machine regression | |
CN111900731A (en) | PMU-based power system state estimation performance evaluation method | |
CN108052717B (en) | Fatigue life calibration method based on local stress-strain method | |
CN114266289A (en) | Complex equipment health state assessment method | |
CN108830405B (en) | Real-time power load prediction system and method based on multi-index dynamic matching | |
CN110889207A (en) | System combination model credibility intelligent evaluation method based on deep learning | |
CN111737993B (en) | Method for extracting equipment health state from fault defect text of power distribution network equipment | |
CN113281229A (en) | Multi-model self-adaptive atmosphere PM based on small samples2.5Concentration prediction method | |
CN116957534A (en) | Method for predicting replacement number of intelligent electric meter | |
CN105912775A (en) | Multimodal modeling method for vehicle axle load data of bridge weight-in-motion system | |
CN109101759A (en) | A kind of parameter identification method based on forward and reverse response phase method | |
CN107017624A (en) | Electric load cycle characteristics modeling method | |
CN113780724A (en) | Method for calculating quantitative evaluation criterion of product quality batch stability | |
CN105528657A (en) | Building earthquake damage prediction method based on Beidou and vector machine | |
Németh et al. | Homogenization of Hungarian daily wind speed data series | |
CN111476392A (en) | Metering device clock error trend prediction method based on social perception | |
CN112434750B (en) | Dam monitoring data development mode identification method based on convolutional neural network | |
Gu et al. | Degradation reliability analysis based on topsis model selection method | |
CN114676587B (en) | Fatigue life evaluation method based on load spectrum similarity | |
Setiawan et al. | Optimization of the Use of Artificial Neural Network Models for Accuracy Data Measurement Palm Oil Production Prediction Rate |
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 |