CN114754973A - Wind tunnel force measurement test data intelligent diagnosis and analysis method based on machine learning - Google Patents
Wind tunnel force measurement test data intelligent diagnosis and analysis method based on machine learning Download PDFInfo
- Publication number
- CN114754973A CN114754973A CN202210561316.2A CN202210561316A CN114754973A CN 114754973 A CN114754973 A CN 114754973A CN 202210561316 A CN202210561316 A CN 202210561316A CN 114754973 A CN114754973 A CN 114754973A
- Authority
- CN
- China
- Prior art keywords
- data
- wind tunnel
- algorithm
- test
- prediction
- 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
- 238000012360 testing method Methods 0.000 title claims abstract description 61
- 238000004458 analytical method Methods 0.000 title claims abstract description 27
- 238000005259 measurement Methods 0.000 title claims abstract description 24
- 238000010801 machine learning Methods 0.000 title claims abstract description 20
- 238000003745 diagnosis Methods 0.000 title claims abstract description 9
- 238000000034 method Methods 0.000 claims abstract description 21
- 238000011156 evaluation Methods 0.000 claims abstract description 11
- 238000012549 training Methods 0.000 claims description 38
- 238000012545 processing Methods 0.000 claims description 16
- 230000002159 abnormal effect Effects 0.000 claims description 5
- 238000013135 deep learning Methods 0.000 claims description 5
- 238000004140 cleaning Methods 0.000 claims description 4
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 238000004519 manufacturing process Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 238000005096 rolling process Methods 0.000 claims description 3
- 238000012706 support-vector machine Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 2
- 238000011161 development Methods 0.000 description 4
- 238000012827 research and development Methods 0.000 description 3
- 239000006185 dispersion Substances 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 239000013598 vector Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M9/00—Aerodynamic testing; Arrangements in or on wind tunnels
- G01M9/08—Aerodynamic models
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M9/00—Aerodynamic testing; Arrangements in or on wind tunnels
- G01M9/06—Measuring arrangements specially adapted for aerodynamic testing
-
- 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
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/23—Design optimisation, verification or simulation using finite element methods [FEM] or finite difference methods [FDM]
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- Computer Hardware Design (AREA)
- Fluid Mechanics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Automation & Control Theory (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Aviation & Aerospace Engineering (AREA)
- Aerodynamic Tests, Hydrodynamic Tests, Wind Tunnels, And Water Tanks (AREA)
Abstract
The invention discloses a wind tunnel force measurement test data intelligent diagnosis and analysis method based on machine learning, and belongs to the field of aerodynamics. The method is used for carrying out intelligent auxiliary analysis such as result prediction, abnormity early warning and the like on test data in the front, middle and rear stages of a large-scale low-speed wind tunnel force measurement test. The method is characterized in that a plurality of algorithms adapted to the wind tunnel force measurement test are combined, fitting degree and error evaluation indexes of each algorithm in the wind tunnel force measurement test are automatically compared, an optimal algorithm adapted to current test data is selected, and intelligent technical auxiliary analysis is further provided for reliability and stability of the pneumatic test. The method can accurately predict and analyze the hexatomic force coefficient of the large-scale low-speed wind tunnel force test, and provides an intelligent technical auxiliary analysis means for the reliability and stability of the large-scale low-speed wind tunnel pneumatic test.
Description
Technical Field
The invention belongs to the field of aerodynamics, and particularly relates to an intelligent diagnosis and analysis method for wind tunnel force measurement test data based on machine learning.
Background
With the continuous development and growth of aviation industry in China, the demand for aircraft development is continuously increased, so that higher requirements are put forward on the development period and the research and development efficiency of the aircraft. The wind tunnel test is taken as a key link in the research and development process of the aircraft, and the intelligent level of the wind tunnel test influences the research and development efficiency of the whole aviation model. The artificial intelligence technology is applied to the wind tunnel test, so that the model development efficiency and the wind tunnel test level can be greatly improved. The conventional wind tunnel force measurement test prediction algorithm adopts a machine learning or deep learning algorithm to predict wind tunnel test data, and although the method can reach a certain precision level, the selected algorithm is not the optimal algorithm although the precision meets the requirement due to different algorithm space complexity degrees and possibly the selected algorithm which is not the most suitable for the current data, and a large amount of time is consumed in the algorithm selection. Therefore, an intelligent diagnosis and analysis method for wind tunnel force measurement test data based on machine learning is needed.
Disclosure of Invention
Based on the defects, the invention aims to provide the intelligent diagnosis and analysis method for the wind tunnel force measurement test data based on machine learning, which combines a plurality of algorithms adapted to the wind tunnel force measurement test, automatically compares the fitting degree and the error evaluation index of each algorithm in the wind tunnel force measurement test, selects the optimal algorithm adapted to the current test data, and further provides intelligent technical auxiliary analysis for the reliability and the stability of the pneumatic test.
The technical scheme adopted by the invention is as follows: a wind tunnel force measurement test data intelligent diagnosis and analysis method based on machine learning comprises the following steps:
the method comprises the following steps: identifying all characteristic variables influencing the six-element force coefficient of the model according to the aerodynamic characteristics of the large-scale low-speed wind tunnel force test, extracting a large amount of historical wind tunnel test data, and processing the data to be used as training data of an algorithm;
step two: establishing a prediction learning machine of a large-scale low-speed wind tunnel test based on a deep learning algorithm of machine learning by utilizing the processed historical data;
step three: and the prediction learning machine is used for carrying out result prediction and intelligent analysis of abnormal early warning on the wind tunnel test result.
Further, the step (1) is specifically as follows: according to the aerodynamic characteristics of a large-scale low-speed wind tunnel force measurement test, test parameters are identified, the incidence angle, the sideslip angle, the aileron, the flap, the slat, the horizontal tail, the elevator and the rudder are determined as input characteristics of an algorithm, the six-membered force coefficients of the lift force, the resistance, the pitching moment, the lateral force, the yawing moment and the rolling moment of a model are determined as output characteristics of a prediction learning machine, training data of the prediction learning machine are obtained from a test historical database according to the identified algorithm input and output variables, data processing operation is carried out on an obtained historical training data set, the training data are divided and combined into a training data set according to input and output, data standardization analysis is adopted to carry out preprocessing on required data, and the formula is as follows:
in the formula:
representing the production parameters of the kth sample under n-dimensional data normalization,
representing that the kth sample arranges N-dimensional metadata according to time series, wherein K is the number of data sets, and N is the number of samples; and then performing data cleaning on the data processing data, including missing value processing and abnormal value processing.
Further, the step (2) is specifically as follows: selecting a support vector machine, a Lasso regression, a Gaussian process regression, a ridge regression and a deep neural network, and establishing a prediction learning machine by using the five machine learning algorithms; training the algorithm in the prediction learning machine by using the processed data, wherein the prediction learning machine forms five different algorithm models when algorithm training is carried out; the mean square error is used as an error evaluation index, and the formula is as follows:
in the formula: i is a training sample label, n is the number of training sample instances, yiFor the training set output value, xijFor the training set input value, betajIs a regression coefficient, and p is the number of the training set features;
selecting the fitting degree as a fitting degree evaluation index output by the algorithm, wherein the formula is as follows:
in the formula: ESS is the regression sum of squares, TSS is the total dispersion sum of squares,
in order to predict the output for the algorithm,
to train sample mean, yiIs a training sample; and (4) sorting the five groups of fitness and mean square error evaluation indexes output by the prediction learning machine, autonomously judging the statistical index of the fitness and the root mean square error by the learning machine, and preferentially selecting the algorithm with the highest fitness and the smallest error as the final prediction algorithm.
Further, the method of step (3) is specifically as follows: and (3) inputting algorithm input data acquired and identified in real time, transmitting the algorithm input data to a prediction learning machine for real-time prediction operation, comparing a real-time prediction value of the prediction learning machine with a real acquisition value of a sensor, and triggering fault early warning by a system when a difference value outside an error allowable range occurs.
The invention has the advantages that: the method is used for carrying out intelligent auxiliary analysis such as result prediction, abnormity early warning and the like on the test data in the front, middle and rear stages of the wind tunnel test, can more clearly and quickly find a more accurate prediction algorithm which is adaptive to the current test data, and provides intelligent technical auxiliary analysis for the reliability and stability of the large-scale low-speed wind tunnel pneumatic test.
Drawings
FIG. 1 is an overall flow chart of the analytical method of the present invention;
FIG. 2 is a data processing flow diagram of the present invention;
FIG. 3 is a flow chart of data cleansing according to the present invention;
Detailed Description
The invention is further illustrated by way of example in the accompanying drawings of the specification:
example 1
The embodiment provides an intelligent diagnosis and analysis method for wind tunnel force measurement test data based on machine learning according to existing large-scale low-speed wind tunnel force measurement test data. The overall working flow of the method is shown in figure 1, and the specific steps are as follows:
step (1): the method comprises the following steps of identifying and processing test parameters of a large-scale low-speed wind tunnel force measurement test, and specifically comprising the following steps:
step (1.1): according to the aerodynamic characteristics of a large-scale low-speed wind tunnel force measurement test, identifying test parameters, determining an attack angle, a sideslip angle, an aileron, a flap, a slat, a horizontal tail, an elevator and a rudder as input characteristics of an algorithm, and determining six-element force coefficients of a lift force, a resistance force, a pitching moment, a lateral force, a yawing moment and a rolling moment of a model as output characteristics of a prediction learning machine;
step (1.2): acquiring training data of a prediction learning machine from a test historical database according to the algorithm input and output variables identified in the step (1.1), performing data processing operation on the acquired historical training data set, and dividing the training data according to input and output to synthesize a training data set;
because the dimensions and units of the data vectors output by simulation are different, the flow chart is shown in fig. 2, and data standardization analysis is adopted to preprocess the required data, and the formula is as follows:
in the formula:
representing the production parameters of the kth sample under n-dimensional data normalization,
it means that the kth sample arranges N-dimensional metadata in time series, K is the number of data sets, and N is the number of samples.
Step (1.3): and (3) performing data cleaning on data processing data, wherein a flow chart is shown in fig. 3, and comprises missing value processing and abnormal value processing, and a mean value/median/mode, a regression method, a lagrange interpolation/newton interpolation method are adopted for interpolation of missing values.
Step (2): establishing a large-scale low-speed wind tunnel test prediction learning machine based on machine learning and deep learning algorithms by utilizing the processed historical data, and specifically comprising the following steps of:
step (2.1): selecting a support vector machine, a Lasso regression, a Gaussian process regression, a ridge regression and a deep neural network, and constructing and combining the five machine learning algorithms by using a Python language and a TensorFlow2.0 frame to form a prediction learning machine for a large-scale low-speed wind tunnel force measurement test;
step (2.2): training an algorithm in a prediction learning machine by using the data processed in the step (1), wherein the prediction learning machine forms five different algorithm models when algorithm training is carried out;
step (2.3): the mean square error is used as an error evaluation index, and the formula is as follows:
in the formula: i is a training sample label, n is the number of training sample instances, yiFor the training set output value, xijFor the training set input value, betajIs a regression coefficient, and p is the number of the training set features;
selecting the fitting degree as a fitting degree evaluation index output by the algorithm, wherein the formula is as follows:
in the formula: ESS is the regression sum of squares, TSS is the total dispersion sum of squares,
in order to predict the output for the algorithm,
to train sample mean, yiAre training samples.
Step (2.4): and (4) sorting the five groups of fitness and mean square error evaluation indexes output by the prediction learning machine, autonomously judging the statistical index of the fitness and the root mean square error by the learning machine, and preferentially selecting the algorithm with the highest fitness and the smallest error as the final prediction algorithm.
And (3): the intelligent analysis and early warning method for the large-scale low-speed wind tunnel force measurement test comprises the following concrete implementation steps:
step (3.1): collecting the identified algorithm input data in real time, and transmitting the algorithm input data to a large low-speed wind tunnel prediction learning machine for real-time prediction operation;
step (3.2): and comparing the real-time predicted value of the prediction learning machine with the real acquisition value of the sensor, and triggering fault early warning by the system when a difference value outside an error allowable range occurs.
According to the method, the aerodynamic characteristics of the existing large-scale low-speed wind tunnel force test are comprehensively considered, advanced means such as machine learning and deep learning are combined, the model six-element force coefficient of the force test is predicted and analyzed, accurate prediction and analysis can be carried out on the six-element force coefficient of the large-scale low-speed wind tunnel force test, and intelligent technical auxiliary analysis is provided for the reliability and stability of the large-scale low-speed wind tunnel pneumatic test.
Claims (4)
1. A wind tunnel force measurement test data intelligent diagnosis and analysis method based on machine learning is characterized by comprising the following steps:
the method comprises the following steps: identifying all characteristic variables influencing the six-element force coefficient of the model according to the aerodynamic characteristics of the large-scale low-speed wind tunnel force test, extracting a large amount of historical wind tunnel test data, and processing the data to be used as training data of an algorithm;
step two: establishing a prediction learning machine of a large-scale low-speed wind tunnel test based on a deep learning algorithm of machine learning by utilizing the processed historical data;
step three: and the prediction learning machine is used for carrying out result prediction and intelligent analysis of abnormal early warning on the wind tunnel test result.
2. The wind tunnel force measurement test data intelligent analysis and early warning method based on machine learning as claimed in claim 1, wherein the step (1) is as follows: according to the aerodynamic characteristics of a large-scale low-speed wind tunnel force measurement test, test parameters are identified, the incidence angle, the sideslip angle, the aileron, the flap, the slat, the horizontal tail, the elevator and the rudder are determined as input characteristics of an algorithm, the six-membered force coefficients of the lift force, the resistance, the pitching moment, the lateral force, the yawing moment and the rolling moment of a model are determined as output characteristics of a prediction learning machine, training data of the prediction learning machine are obtained from a test historical database according to the identified algorithm input and output variables, data processing operation is carried out on an obtained historical training data set, the training data are divided and combined into a training data set according to input and output, data standardization analysis is adopted to carry out preprocessing on required data, and the formula is as follows:
in the formula:
representing the production parameters of the kth sample under n-dimensional data normalization,
representing that the kth sample arranges N-dimensional metadata according to time series, wherein K is the number of data sets, and N is the number of samples; and then performing data cleaning on the data processing data, wherein the data cleaning comprises missing value processing and abnormal value processing.
3. The wind tunnel dynamometry test data intelligent analysis and early warning method based on machine learning as claimed in claim 2, wherein step (2) is as follows: selecting a support vector machine, a Lasso regression, a Gaussian process regression, a ridge regression and a deep neural network, and establishing a prediction learning machine by using the five machine learning algorithms; training an algorithm in the prediction learning machine by using the processed data, wherein the prediction learning machine forms five different algorithm models when algorithm training is carried out; the mean square error is used as an error evaluation index, and the formula is as follows:
in the formula: i is a training sample label, n is the number of training sample instances, yiFor the training set output value, xijFor the training set input value, betajIs a regression coefficient, and p is the number of the training set features;
selecting the fitting degree as a fitting degree evaluation index output by the algorithm, wherein the formula is as follows:
in the formula: ESS isAnd returning to the sum of squares, TSS is the sum of squared deviations,
in order to predict the output for the algorithm,
to train sample mean, yiIs a training sample; and (4) sorting the five groups of fitness and mean square error evaluation indexes output by the prediction learning machine, autonomously judging the statistical index of the fitness and the root mean square error by the learning machine, and preferentially selecting the algorithm with the highest fitness and the smallest error as the final prediction algorithm.
4. The machine learning-based wind tunnel force measurement test data intelligent analysis and early warning method according to claim 3, wherein the step (3) is as follows: and (3) inputting algorithm input data acquired and identified in real time, transmitting the algorithm input data to a prediction learning machine for real-time prediction operation, comparing a real-time prediction value of the prediction learning machine with a real acquisition value of a sensor, and triggering fault early warning by a system when a difference value outside an error allowable range occurs.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210561316.2A CN114754973A (en) | 2022-05-23 | 2022-05-23 | Wind tunnel force measurement test data intelligent diagnosis and analysis method based on machine learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210561316.2A CN114754973A (en) | 2022-05-23 | 2022-05-23 | Wind tunnel force measurement test data intelligent diagnosis and analysis method based on machine learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114754973A true CN114754973A (en) | 2022-07-15 |
Family
ID=82334338
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210561316.2A Pending CN114754973A (en) | 2022-05-23 | 2022-05-23 | Wind tunnel force measurement test data intelligent diagnosis and analysis method based on machine learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114754973A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115290286A (en) * | 2022-10-10 | 2022-11-04 | 中国空气动力研究与发展中心高速空气动力研究所 | Integrated learning evaluation system for flow field stability of sub-span supersonic wind tunnel |
| CN115808284A (en) * | 2023-02-09 | 2023-03-17 | 中国空气动力研究与发展中心设备设计与测试技术研究所 | Wind tunnel multi-working condition modeling method based on neural network parameter scheduling |
| CN116305588A (en) * | 2023-05-17 | 2023-06-23 | 中国航空工业集团公司沈阳空气动力研究所 | Wind tunnel test data anomaly detection method, electronic equipment and storage medium |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103335814A (en) * | 2013-06-09 | 2013-10-02 | 电子科技大学 | Inclination angle measurement error data correction system and method of experimental model in wind tunnel |
| WO2016061283A1 (en) * | 2014-10-14 | 2016-04-21 | Skytree, Inc. | Configurable machine learning method selection and parameter optimization system and method |
| CN106127242A (en) * | 2016-06-21 | 2016-11-16 | 河海大学 | Year of based on integrated study Extreme Precipitation prognoses system and Forecasting Methodology thereof |
| CN109523316A (en) * | 2018-11-16 | 2019-03-26 | 杭州珞珈数据科技有限公司 | The automation modeling method of commerce services model |
| CN111275288A (en) * | 2019-12-31 | 2020-06-12 | 华电国际电力股份有限公司十里泉发电厂 | XGboost-based multi-dimensional data anomaly detection method and device |
| CN112509702A (en) * | 2020-11-30 | 2021-03-16 | 质美(北京)生物科技有限公司 | Disease prediction method and system based on medical big data |
| CN112577706A (en) * | 2020-12-25 | 2021-03-30 | 中国航天空气动力技术研究院 | Method for acquiring pose of embedded wind tunnel free flight test model |
| CN113609677A (en) * | 2021-08-05 | 2021-11-05 | 东南大学 | Multipath-based machine learning auxiliary antenna design method |
| CN113919230A (en) * | 2021-10-20 | 2022-01-11 | 中国兵器装备集团自动化研究所有限公司 | Modeling evaluation method and system for operation of complex equipment |
| CN114036989A (en) * | 2021-12-17 | 2022-02-11 | 北京航空航天大学 | Laser Doppler signal processing method and system based on machine learning |
| US20220147897A1 (en) * | 2020-11-12 | 2022-05-12 | SparkCognition, Inc. | Machine learning for predictive optmization |
| CN114484731A (en) * | 2021-12-27 | 2022-05-13 | 浙江英集动力科技有限公司 | Method and device for diagnosing faults of central air conditioner based on stacking fusion algorithm |
-
2022
- 2022-05-23 CN CN202210561316.2A patent/CN114754973A/en active Pending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103335814A (en) * | 2013-06-09 | 2013-10-02 | 电子科技大学 | Inclination angle measurement error data correction system and method of experimental model in wind tunnel |
| WO2016061283A1 (en) * | 2014-10-14 | 2016-04-21 | Skytree, Inc. | Configurable machine learning method selection and parameter optimization system and method |
| CN106127242A (en) * | 2016-06-21 | 2016-11-16 | 河海大学 | Year of based on integrated study Extreme Precipitation prognoses system and Forecasting Methodology thereof |
| CN109523316A (en) * | 2018-11-16 | 2019-03-26 | 杭州珞珈数据科技有限公司 | The automation modeling method of commerce services model |
| CN111275288A (en) * | 2019-12-31 | 2020-06-12 | 华电国际电力股份有限公司十里泉发电厂 | XGboost-based multi-dimensional data anomaly detection method and device |
| US20220147897A1 (en) * | 2020-11-12 | 2022-05-12 | SparkCognition, Inc. | Machine learning for predictive optmization |
| CN112509702A (en) * | 2020-11-30 | 2021-03-16 | 质美(北京)生物科技有限公司 | Disease prediction method and system based on medical big data |
| CN112577706A (en) * | 2020-12-25 | 2021-03-30 | 中国航天空气动力技术研究院 | Method for acquiring pose of embedded wind tunnel free flight test model |
| CN113609677A (en) * | 2021-08-05 | 2021-11-05 | 东南大学 | Multipath-based machine learning auxiliary antenna design method |
| CN113919230A (en) * | 2021-10-20 | 2022-01-11 | 中国兵器装备集团自动化研究所有限公司 | Modeling evaluation method and system for operation of complex equipment |
| CN114036989A (en) * | 2021-12-17 | 2022-02-11 | 北京航空航天大学 | Laser Doppler signal processing method and system based on machine learning |
| CN114484731A (en) * | 2021-12-27 | 2022-05-13 | 浙江英集动力科技有限公司 | Method and device for diagnosing faults of central air conditioner based on stacking fusion algorithm |
Non-Patent Citations (2)
| Title |
|---|
| 姜金俊 等: "风洞试验方案智能优化设计方法研究", 《实验流体力学》 * |
| 翟立宾: "基于机器学习方法的柔性圆柱涡激振动预报", 《中国优秀硕士学位论文全文数据库》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115290286A (en) * | 2022-10-10 | 2022-11-04 | 中国空气动力研究与发展中心高速空气动力研究所 | Integrated learning evaluation system for flow field stability of sub-span supersonic wind tunnel |
| CN115290286B (en) * | 2022-10-10 | 2023-01-24 | 中国空气动力研究与发展中心高速空气动力研究所 | Integrated learning evaluation system for flow field stability of sub-span supersonic wind tunnel |
| CN115808284A (en) * | 2023-02-09 | 2023-03-17 | 中国空气动力研究与发展中心设备设计与测试技术研究所 | Wind tunnel multi-working condition modeling method based on neural network parameter scheduling |
| CN116305588A (en) * | 2023-05-17 | 2023-06-23 | 中国航空工业集团公司沈阳空气动力研究所 | Wind tunnel test data anomaly detection method, electronic equipment and storage medium |
| CN116305588B (en) * | 2023-05-17 | 2023-08-11 | 中国航空工业集团公司沈阳空气动力研究所 | Wind tunnel test data anomaly detection method, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114754973A (en) | Wind tunnel force measurement test data intelligent diagnosis and analysis method based on machine learning | |
| CN111275288A (en) | XGboost-based multi-dimensional data anomaly detection method and device | |
| CN114619292B (en) | Milling cutter wear monitoring method based on fusion of wavelet denoising and attention mechanism with GRU network | |
| CN109829236A (en) | A kind of Compressor Fault Diagnosis method based on XGBoost feature extraction | |
| CN110737976B (en) | Mechanical equipment health assessment method based on multidimensional information fusion | |
| CN110685868A (en) | Wind turbine generator fault detection method and device based on improved gradient elevator | |
| CN111680875B (en) | Unmanned aerial vehicle state risk fuzzy comprehensive evaluation method based on probability baseline model | |
| CN115048874B (en) | Aircraft design parameter estimation method based on machine learning | |
| CN109934422B (en) | Neural network wind speed prediction method based on time series data analysis | |
| CN111768000A (en) | Industrial process data modeling method for online adaptive fine-tuning deep learning | |
| CN111369045A (en) | Method for predicting short-term photovoltaic power generation power | |
| CN113780153A (en) | Cutter wear monitoring and predicting method | |
| CN111079343A (en) | Wind turbine generator effective wind speed estimation method based on width learning | |
| CN115099296A (en) | Sea wave height prediction method based on deep learning algorithm | |
| CN113567159A (en) | Scraper conveyor state monitoring and fault diagnosis method based on edge cloud cooperation | |
| CN115186574A (en) | Tool residual life prediction method based on gated cyclic residual error network | |
| CN112734131B (en) | Fan blade icing state prediction method based on deep learning algorithm | |
| CN114897138A (en) | System fault diagnosis method based on attention mechanism and depth residual error network | |
| CN114879628A (en) | Multi-mode industrial process fault diagnosis method based on local maximum mean difference resistance | |
| CN112763215B (en) | Multi-working-condition online fault diagnosis method based on modular federal deep learning | |
| CN112036470A (en) | Cloud transmission-based multi-sensor fusion cucumber bemisia tabaci identification method | |
| CN116738332A (en) | Aircraft multi-scale signal classification recognition and fault detection method combining attention mechanism | |
| CN114781551B (en) | Battery multi-fault intelligent classification and identification method based on big data | |
| CN114595750A (en) | Aluminum electrolysis fault identification method based on deep reinforcement learning parameter automatic adjustment | |
| CN107341503B (en) | Identification method for multi-source energy efficiency state in cutting process |
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 |
Application publication date: 20220715 |
|
| RJ01 | Rejection of invention patent application after publication |