Table of Content

25 June 2021, Volume 39 Issue 3

Previous Issue    Next Issue

Civil Aviation

Congestion prediction of flow system of air traffic network based on GA-BP neural network

ZHANG Zhaoning , ZHANG Yingying , JI Shanshan

2021, 39(3):  1-5. 

Asbtract ( 1267 )  

References | Related Articles | Metrics

From the perspective of the air traffic network flow system, the large-scale flight delay problem is converted into the congestion problem of the air traffic network flow system, and its congestion prediction is performed. Firstly, the relationship between capacity, flow and flow demand of the air traffic network flow system is analyzed, and the four forecast indicators including flow demand, cumulative delay flight change rate, capacity change in the previous period and capacity change in period are extracted using congestion degree as a congestion evaluation index. Then based on genetic algorithm(GA) optimization back propagation(BP) neural network, a congestion prediction model is established to predict the degree of congestion. Finally, the actual data of an air traffic network flow system is used to analyze examples. The results show that the model has a good prediction and can provide a decision basis for the air traffic flow management department.

Track identification in terminal airspace based on self-organizing neural network 

XIE Chunsheng , ZHAO Long , LIU Yuepeng

2021, 39(3):  6-9. 

Asbtract ( 1326 )  

References | Related Articles | Metrics

The trajectory pattern recognition can further support track prediction, airspace structure optimization and air traffic situation monitoring. Firstly, a series of trajectory point sets are formed by screening and processing the initially obtained automatic dependent surveillance-broadcast (ADS-B) data. Secondly, the similarity degree between trajectory data composed of trajectory points is calculated. The training set and test set are selected according to a certain ratio; then, the training set is used for learning and training, and a self-organizing neural network (SONN) is established to obtain a competition unit. Finally, the test set is input and identified by the resulting neural network to analyze its correctness. Simulation results show that the algorithm can better identify the trajectory in the airspace of terminal area.

Fast detection method of signal interference on Beidou B1 signal 

LIU Ruihua, ZHANG Shuo

2021, 39(3):  10-15. 

Asbtract ( 1744 )  

References | Related Articles | Metrics

Interference detection is the basis of interference monitoring, which can effectively ensure the quality of Beidou B1 signal. Due to the poor detection performance of traditional CME (consecutive mean excision) algorithm, large amount of computation work of FCME(forward consecutive mean excision) and double threshold FCME algorithm makes it difficult to achieve fast interference detection. Therefore, an improved algorithm based on FCME is proposed. Firstly, according to the operational characteristics of FFT (fast Fourier transform), the interference detection sample points are reduced; then the differential algorithm is used to replace the sorting algorithm in FCME and calculate the initial threshold, so as to reduce the complexity of the algorithm; finally, the algorithm is verified by the measured data, and results show that the improved detection algorithm can effectively reduce the computational complexity, and has good detection performance for interference signals.

Flight control and simulation of quad-rotor UAV under wind field disturbance 

YANG Yonggang , SONG Wei

2021, 39(3):  16-21. 

Asbtract ( 2930 )  

References | Related Articles | Metrics

Aiming at the problem that quad-rotor UAV is usually disturbed by wind in the field, a flight control method of quad-rotor UAV under wind disturbance is proposed. Based on force analysis of quad-rotor UAV, the nonlinear mathematical model is established by considering the gyroscope effect, and the external wind field disturbance is introduced to establish the dynamic model under the action of wind field. The backstep controller is designed to realize the position and attitude control of the quad-rotor UAV. Lyapunov stability theory is used to prove the stability of the system, and Matlab/Simulink is used to simulate and analyze the control strategy effect. Under the action of natural wind, this model accurately reflects the dynamic characteristics of the system, and the backstep controller can also track the trajectory of the four-rotor UAV, which has good stability

Damage detection of aero-engine blades based on improved ZF network 

XING Zhiwei , LI Longpu , HOU Xiangkai , SHI Yazhong , WANG Hao

2021, 39(3):  22-28. 

Asbtract ( 3102 )  

References | Related Articles | Metrics

In order to achieve the accurate detection of aero-engine blade damages, a Zeiler-Fergus(ZF) network improvement method based on the faster region-based convolutional neural network(Faster R-CNN) model is proposed. Firstly, the aero-engine blades damage detection is abstracted as the object detection problem, and aiming at the problem, a ZF network is used to detect the damage location and type. Then, some convolutional layers are added into the original ZF network according to the detection effect. Hyper -parameters such as kernel size in the convolutional layers and the stride size in the pooling layers are adjusted, and the added convolutional layers are included in the shared convolutional layers to extract more detailed damage features. Finally, the existing dataset is divided into three sub-datasets, on which the network performance before and after improvedment is experimentally compared. Results show that the mean average precision of the improved ZF network is up to 5.5% compared with that of the original network, which proves that the improved ZF network can predict engine blades damage more accurately

Fault diagnosis of aero-engine gas path based on GA-LSSVM 

TIAN Jing, HU Hexiang

2021, 39(3):  29-33. 

Asbtract ( 1439 )  

References | Related Articles | Metrics

Aiming at the lack of data sample and nonlinearity of aero-engine gas-path fault, the genetic algorithm (GA) optimized least square support vector machine (LSSVM) is applied to aero-engine gas-path fault diagnosis. Firstly, the key parameters of LSSVM algorithm is analyzed, and the regularization parameter(C) and kernel parameter ( g ) of LSSVM are optimited with GA. Secondly, GA-LSSVM is used to diagnose the gas path fault of a biaxial turbofan engine. Finally, SVM, LSSVM, GA-SVM and GA-LSSVM are compared from three aspects of diagnosis accuracy, anti-noise ability and training time. Results show that GA-LSSVM is superior to the other three algorithms in diagnosis accuracy and anti noise intensity, but its training time is longer due to the optimization process of GA-LSSVM.

Design and optimization of deformable wing driven by shape memory alloy 

LIU Bingfei, ZHANG Chao, ZHANG Wei

2021, 39(3):  34-38. 

Asbtract ( 1644 )  

References | Related Articles | Metrics

The aerodynamic performance of wings designed by traditional methods strongly depends on flight conditions. Aiming at this problem, a deformable wing structure driven by shape memory alloy(SMA) wire is designed. The structure can automatically adjust the wing shape according to different flight states, so as to simultaneously optimize its aerodynamic performance. Firstly, the driving point of SMA driver is connected to the stringer inside the airfoil to drive the stringer up and down and deform the flexible skin. Secondly, by using the integrated optimization platform of Isight , the wing modelling and hydrodynamics analysis are conducted to achieve the optimal design of deformable wing. Finally, basing on the optimization design results and SMA constitutive relation, the driving structure scheme of deformable wing is determined. Research results show that the SMA driver can realize the deformation driving of the deformable wing, through temperature control in the range of 30- 140 ℃, the deformation of the upper and lower skins of the wing can be achieved by 0-8 mm, and the maximum lift-to-drag ratio can be increased by 21.87%.

Comprehensive evaluation on ability of handling emergency situation of civil aviation crew

LI Ye, LI Pengfei , WANG Shuo , LI Shu, WANG Lei

2021, 39(3):  39-44. 

Asbtract ( 1544 )  

References | Related Articles | Metrics

Pilot’s emergency situation handling ability is directly related to the safety performance of flight crew. Through document analyses and expert interviews, emergency situation handling ability of flight crews is divided into three dimensions including knowledge, skills and individual qualities; by further designing and distributing questionnaires, 26 valid questionnaires are obtained, indices weights are determined by applying of the entropy weight method, a complete evaluation index system of emergency situation handling ability is built. Combining with the scores of airline N, the evaluation result of cloud model show that the emergency situation handling ability of flight crews of airline N is in a good level. The current evaluation index system can provide reference for pilot selection and evidence-based training.

Security evaluation standardization method for civil aviation information system 

HAN Yanzheng, ZHANG Xugao , QIU Xiaorui , WANG Yong, JIANG Laiwei

2021, 39(3):  45-48. 

Asbtract ( 1325 )  

References | Related Articles | Metrics

Aiming at the quantifying difficulty of security evaluation for civil aviation information system due to various kinds of evaluation indicators, a standardization method for security evaluation is proposed. Firstly, the evaluation indicators are divided into qualitative and quantitative indicators of compliance degree of security. Then, description tables of compliance degree of security and index matrix tables of compliance degree of security are set for qualitative indicators, quantitative indicators are divided into positive indicators and reverse indicators. Finally, the normalized operator is used to transform the evaluation results into percentile form. The standardization method can provide a relatively intuitive reference for security managers to understand the security status of information systems.

Airworthiness Column

Influence of rain ingestion on aerodynamic performance of aero-engine fan 

BAI Jie , CHEN Yankang, FU Wenguang, SUN Peng

2021, 39(3):  49-55. 

Asbtract ( 1349 )  

References | Related Articles | Metrics

In order to investigate the influence of rain ingestion on the aerodynamic performance of aero-engine fan, fan component of DGEN380 is taken as research object, numerical simulation is conducted to explore the influence of different rain ingestion volumes and raindrop diameters on the aerodynamic performance of the fan, and the variation of flow field with different rain ingestion volumes is analyzed emphatically. Results show that all the three indicators including fan efficiency， pressure ratio, and stability margin decrease with the increase of rain ingestion volume, and the greater the rain ingestion volume becomes, the greater the decline is. When the rain ingestion volume is 4% and the raindrop diameter is 0.5 mm, 1.0 mm and 2.0 mm, the pressure ratio of the fan changes little, the efficiency decreases mainly near the block boundary. Under the conditions of 0%, 4% and 8% rain ingestion volume, loss caused by wake and tip leakage vortices in fan rotor passage increases with the increase of rain ingestion volume; the mixing loss caused by raindrops increases in the high region of the upper lobe of stator channel.

Engineering and Technology

Top-N recommendation algorithm based on user’s interest drift 

LIU Haohan, MA Xiaolu, HE Huaiqing

2021, 39(3):  56-61. 

Asbtract ( 1350 )  

References | Related Articles | Metrics

Traditional recommendation algorithms are mostly based on the static attributes of users without considering the drift of user’s interest. To this end, Top-N recommendation algorithm integrating user’s interest drift detection is proposed. The new algorithm makes full use of long short-term memory(LSTM) in processing time series data to represent short -term interest shift of users, compromises a fixed vector obtained by matrix factorization to represent long-term interest of users, and incorporates the attention mechanism into the representation of hidden state of the long short-term memory network to obtain the effect of the user’s long-term interest on the shortterm interest. Compared with current popular algorithms, performance of the proposed algorithm is superior in Top-N item recommendation.

Basic Science

Construction of new codebook based on affine space over finite field 

LIU Xuemei, JIA Lihua

2021, 39(3):  62-64. 

Asbtract ( 1096 )  

References | Related Articles | Metrics

Codebooks are widely applied in code division multiple access systems to separate the signals of different users. Basing on the affine spaces over finite fields, a class of new codebooks are constructed. By the counting theorems of affine spaces, parameters of the codebook are obtained. Sufficient and necessary conditions for the codebooks are given to meet the Welch bound, and the conditions for the the maximum cross correlation amplitude astmptotically attains to the Welch bound are calculated.