Table of Content

28 October 2023, Volume 41 Issue 2

Previous Issue    Next Issue

Civil Aviation

Research on evaluation index of pilot ability based on information processing model

WANG Lei, ZHANG Mengxi, ZOU Ying, CAI Yiwei

2023, 41(2):  1-7. 

Asbtract ( 992 )  

References | Related Articles | Metrics

In order to achieve the evaluation of pilot ability corresponding to the post competency requirements and promote the dynamic monitoring of pilot competency status, this study constructed the ability evaluation index system of pilot based on the information processing model, in combination with the requirements of the professionalism lifecycle management system (PLM). Firstly, the relationship between the information processing model and the capabilities was described. Then， based on the information processing model, the required ability elements in each segment of information processing and in the psychological activities of completing driving operations and coping with complex situations were analyzed. Finally, the ability evaluation indicators were verified based on expert survey. The verified evaluation index system of pilot ability conformed to the requirements of occupational aptitude psychology, including 14 secondary indicators of 3 dimensions. The pilot ability evaluation index system proposed in this study can lay a foundation for the subsequent construction of the psychological competency evaluation index system and the development of evaluation tools, as well as provide a theoretical basis for the psychological selection and evaluation of pilot.

Research on fire evolution mechanism of terminal buildings coupled with fire fighting facilities

SONG Yang , ZHANG Kaiwen , JIANG Hongxiao

2023, 41(2):  8-13. 

Asbtract ( 775 )  

References | Related Articles | Metrics

Airport terminal is a large public building, it can easily cause smoke accumulation and make evacuation difficult once a fire occurs. Traditional fire fighting facilities are difficult to meet the fire fighting needs of such buildings.

In this paper, the evolution mechanism of coupled fire facilities is studied. Firstly, the building information modeling (BIM) of terminal hall is established, and the fire simulation of terminal in different scenarios is carried out through fire dynamics simulator (FDS). Then the data of sprinkler operation, smoke layer height, visibility and heat release rate in different regions and different scenarios are obtained. The fire evolution mechanism is analyzed according to the changing process. The results show that there is a significant difference in the fire evolution mechanism between the coupled fire fighting facilities and the non-start-up fire fighting facilities for the special public building such as airport terminal. At the same time, the simulation results can provide ideas for the optimization of fire fighting design and the formulation of emergency evacuation plan of airport terminal.

Detection method for code defect based on LSTM-Seq2Seq model with large perception

WANG Peng , YAO Xinpeng , WANG Kenian , CHEN Wenqi , CHEN Xi

2023, 41(2):  14-20. 

Asbtract ( 629 )  

References | Related Articles | Metrics

Aiming at the problem that the existing deep neural network based code defect detection methods cannot analyze the defect characteristics and output relevant review suggestions, a code defect detection method based on LSTM-Seq2Seq model with large perception is proposed. Firstly, the long short-term memory network (LSTM) is applied to obtain the coding characteristics of defective code and establish a defect identification model.

Secondly, aiming at the mismatch between model and dataset, the code segment length coefficient is introduced into the sequence to sequence (Seq2Seq) model to improve the model applicability to the code review task. To realize the review output function, the code analysis model is constructed by establishing the mapping relationship between the features of code defect and the review recommendation. Finally, the method is verified by the open data set of SARD. The results show that the accuracy rate, recall rate and F1 vale of the proposed method are 92.50%, 87.20% and 87.60% respectively, and the similarity between the output review of typical code defect and the expert review is 85.99%, which can effectively reduce the dependence on expert experience in the review process

Quantification of controlled flight into terrain event based on Bayesian network

LIU Junjie, YE Yinghao, DU Yinlan

2023, 41(2):  21-26. 

Asbtract ( 843 )  

References | Related Articles | Metrics

Choosing the information of controlled flight into terrain(CFIT) as the research object, a three-layer Bayesian network model including event consequence layer, aircraft status layer and inducing layer is established according to the analysis of the CFIT event evolution process based on basic element analysis method. Taking the CFIT event data collected by civil aviation of China from 2017 to 2019 and Aviation Safety Network (ASN) in recent 20 years (2000-2019) as samples, the parameters of network nodes are established. The known nodes and target nodes of Bayesian network are selected by GeNIe for quantitative analysis, to obtain the possibility ranking, most probable target nodes and impact intensity of target nodes. Finally, the key risk processes of the CFIT, namely flight altitude control, crew loss of situational awareness, flight support and corresponding quantitative results, are obtained to provide data support for strengthening the risk control of the CFIT events.

Research on airworthiness regulations of flight control system of transport rotorcraft

CHEN Yujin, LI Hong

2023, 41(2):  27-32. 

Asbtract ( 784 )  

References | Related Articles | Metrics

The CCAR 29.671 general clause for flight control system of transport rotorcraft only gives the airworthiness safe鄄 ty objectives and requirements at the top level, which is insufficient in the airworthiness certification recommen鄄 dations required for engineering practice. Based on the analysis of airworthiness rules and technical standards, combining with actual engineering practice, this paper gives qualitative and quantitative insights on the airwor鄄 thiness requirements and compliance methods of this clause. Advices on the airworthiness requirements and compliance methods in the aspect of flight control of fly-by-wire are proposed.

Multi-objective gate assignment considering time execution deviation

ZHU Chengyuan , WANG Zhiwei , WANG Yipeng

2023, 41(2):  33-38. 

Asbtract ( 699 )  

References | Related Articles | Metrics

Aiming at the gate assignment problem that there was large time execution deviation in actual operation, the feasibility that reduce time execution deviation using total airspace and airport modeller (TAAM) was discussed.

A model was established with the boarding time of passengers, unbalanced gate occupation, and balance of average taxiing distance of airlines as targets. First, TAAM tool was used to simulate and optimize scheduled gate operation time, and got initial solution of gate assignment. And then entropy-weight method was applied to transform multi-objective into single objective problem. Finally, Tabu algorithm was used to solve the proposed model. The simulation results of verifying the time execution deviation before and after the optimization of gate operation showed that after the optimization, time execution deviation was significantly improved, and the efficiency of gate operation was effectively increased.

Comprehensive evaluation model of system-level electromagnetic susceptibility

GONG Fengxun, SUN Jian

2023, 41(2):  39-46. 

Asbtract ( 880 )  

References | Related Articles | Metrics

A system-level electromagnetic susceptibility comprehensive evaluation model is established , and three description parameters including error threshold, system failure probability and alarm time are proposed. First, by analyzing the principle of electromagnetic interference caused errors of system-related performance indicators, error modeling and threshold solving are carried out to realize the quantitative prediction of electromagnetic susceptibility. Then, under this error threshold condition, the fault tree is applied to analyze the system failure probability and establish the failure probability model. Finally, the system alarm time model is established under the premise of system failure. Taking a multi-point positioning receiving system as an example, the experimental simulation verification results show that the average error between the interference threshold predicted by the proposed model and the measured data is within the engineering allowable range. Compared with the classic Volterra behavioral model, the proposed comprehensive evaluation model can not only achieve the effect of predict sensitivity threshold, but also theoretically evaluate the probability of system failure and the mathematical expectation of failure time in the current environment.

Joint extraction method of entity relationship based on coding feature fusion of BERT-CNN

DING Jianli SU Wei

2023, 41(2):  47-53. 

Asbtract ( 1036 )  

References | Related Articles | Metrics

In view of the complex structure of the existing entity relationship extraction model and the poor extraction effect, a joint extraction method of entity relationship based on pre -training coding feature fusion of bidirectional encoder representation from transformers (BERT) and convolutional neural network (CNN) is proposed. First, the position of the beginning and end of the subject is predicted based on the sentence vector encoded by BERTCNN. Secondly, the feature vector of the predicted first and last position index sentence is used as the head and tail vector of the predicted subject, and then the head and tail vectors of the predicted subject are feature-fused to obtain the subject vectors based on the product method. Then, the subject vector and the sentence vector are fused by the product method to obtain a new sentence encoding vector, which guides the prediction of the head and tail positions of the object under different relationships and obtains entity relationship triplet. In order to verify the effect of the proposed model, this model and other similar algorithms are tested with the public data sets of NYT and WebNLG. The accuracy and recall rate of this model are better than those of the compared model, and the F1 values reach to 92.75% and 93.19%, respectively

Fault analysis on LPC 2.5 bleed system of V2500-A5 engine

BAI Jie , HE Sihong

2023, 41(2):  54-57. 

Asbtract ( 1291 )  

References | Related Articles | Metrics

The low pressure compressor (LPC) 2.5 bleed system of the V2500-A5 engine is an important component to ensure the safe and reliable operation of the engine. Aiming at the actual case of 2.5 bleed system of this type of engine failure and the troubleshooting cases in recent years, through literature analysis and case studies, combining with a domestic airline′s fleet failure data, the composition, classification and solution methods of this system failure are analyzed. Monitoring and prevention method for 2.5 bleed valve damage is proposed, which can provide a reference for airlines and engine overhaul plants to monitor and repair this failure.

Research on flight simulation system of unmanned helicopter based on Vega Prime

SHI Yongsheng, XIA Zhichao

2023, 41(2):  58-64. 

Asbtract ( 803 )  

References | Related Articles | Metrics

A flight simulation system was designed taking an unmanned helicopter as the simulation object, which consisted of four parts: flight simulation module, cockpit simulation module, visual simulation module and console module.

The flight simulation module built the dynamic models of rotor, tail rotor, fuselage, horizontal tail and vertical tail, and the Simulink module was written by S function. The photo-level flight instrument was designed by GL Studio software for real-time display of flight data. The visual simulation module was redeveloped based on Vega Prime simulation platform. The basic simulation framework was built and the console interface was designed by multithread method based on MFC (microsoft foundation classes), which was used for real-time interaction with users.

Finally, the feasibility of the system was verified by simulation.