ACTA AERONAUTICAET ASTRONAUTICA SINICA >
BP neural network⁃based quantitative classification model for safety in experimental flight training
Received date: 2023-12-08
Revised date: 2023-12-11
Accepted date: 2024-01-05
Online published: 2024-01-11
Supported by
National Level Project
To enhance the safety of test pilots during aviation experimental flights and reduce the risk level of experimental flights， a quantitative analysis model for the safety classification of experimental flight training is developed based on the Back-Propagation （BP） neural network. Adopting a human factor engineering perspective， the factors influencing test flight safety during the experimental flight training process are analyzed. Three key components， namely the human factor， aircraft factor， and environmental factor， are chosen for the analysis. A structured system of quantitative analysis indicators for safety classification during the experimental flight training process is established， focusing on the pivotal elements of human factors， specific experimental training subjects， and environmental conditions. After quantifying the human factors engineering indicators， due to the relatively low similarity in the fused data types， the BP neural network is employed to construct a quantitative analysis model for safety classification in experimental flight training. Following model training and testing， a quantified safety classification level for the experimental flight training process is output. Utilizing customized tactile acquisition devices and a non-contact facial recognition system， the physiological rhythm data of test pilots during the execution of experimental flight training subjects are collected. The analysis focuses on understanding the impact of the complexity and difficulty of training subjects on the psychological and physiological characteristics of test pilots. On this basis， the quantitative metrics and warning indicators are established， allowing for optimization of experimental flight training subjects， improvement of training quality， and the assurance of test flight safety. The experiments indicate that the output deviation of the quantitative classification model for safety in the experimental flight training process is less than 2%. The model’s predicted results closely align with the actual risk levels observed during the training process， showing that the model proposed can be effectively utilized for risk warning during experimental flight training， and thereby enhance the quality of pilot training and provide reliable safeguard for actual test flight safety.
Fei MA , Qiong ZHANG , Peijun LAI , Yidi YUE . BP neural network⁃based quantitative classification model for safety in experimental flight training[J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2024 , 45(5) : 529957 -529957 . DOI: 10.7527/S1000-6893.2024.29957
| 1 | HAFEZI ZADEH N， MOVAHEDI M M， AHMAD SHAYANNIA S. Human resource scheduling in project management using the simulated annealing algorithm with the human factors engineering approach［J］. Discrete Dynamics in Nature and Society， 2022， 2022： 3597014. |
| 2 | 钱泱， 李文清， 段文华. 水电厂作业现场风险等级动态评价及应用［J］. 水电能源科学， 2022， 40（8）： 177-180. |
| QIAN Y， LI W Q， DUAN W H. Dynamic evaluation and application of risk grade in operation site of hydropower plant［J］. Water Resources and Power， 2022， 40（8）： 177-180 （in Chinese）. | |
| 3 | 王永刚， 何定坤. 飞行员持续飞行安全能力评价模型［J］. 中国民航大学学报， 2022， 40（4）： 61-64. |
| WANG Y G， HE D K. Evaluation model of continuous flight safety capability of pilots［J］. Journal of Civil Aviation University of China， 2022， 40（4）： 61-64 （in Chinese）. | |
| 4 | 韩国玺， 张曙光， 李志涛. 民用飞机高原风场进近驾驶行为变化对失控趋势的影响［J］. 航空学报， 2015， 36（6）： 1775-1787. |
| HAN G X， ZHANG S G， LI Z T. Influence on loss of control trend by pilot behavior changes during highland wind-field approach［J］. Acta Aeronautica et Astronautica Sinica， 2015， 36（6）： 1775-1787 （in Chinese）. | |
| 5 | 苏畅， 张恒喜. 飞机作战效能评估中人的可靠性的引入方法［J］. 航空学报， 2006， 27（2）： 262-266. |
| SU C， ZHANG H X. Method of considering human reliability in combat effectiveness evaluation of aircraft［J］. Acta Aeronautica et Astronautica Sinica， 2006， 27（2）： 262-266 （in Chinese）. | |
| 6 | 姚裕盛， 徐开俊. 基于BP神经网络的飞行训练品质评估［J］. 航空学报， 2017， 38（S1）： 721513. |
| YAO Y S， XU K J. Evaluation of flight training quality based on BP neural network［J］. Acta Aeronautica et Astronautica Sinica， 2017， 38（S1）： 721513 （in Chinese）. | |
| 7 | 刘浩， 王昊， 孟光磊， 等. 基于动态贝叶斯网络和模糊灰度理论的飞行训练评估［J］. 航空学报， 2021， 42（8）： 525838. |
| LIU H， WANG H， MENG G L， et al. Flight training evaluation based on dynamic Bayesian network and fuzzy gray theory［J］. Acta Aeronautica et Astronautica Sinica， 2021， 42（8）： 525838 （in Chinese）. | |
| 8 | 张琼， 彭天池， 王俊杰. 基于场景的国产民机试飞安全培训体系建设实践［J］. 民航管理， 2021（6）： 76-80. |
| ZHANG Q， PENG T C， WANG J J. Practice of building scenario-based safety training system for domestic civil aircraft test flight［J］. Civil Aviation Management， 2021（6）： 76-80 （in Chinese）. | |
| 9 | 石娟， 常丁懿， 郑鹏. 基于BP神经网络的建筑工人不安全行为预警模型［J］. 中国安全科学学报， 2022， 32（1）： 27-33. |
| SHI J， CHANG D Y， ZHENG P. An early warning model of unsafe behaviors of construction workers based on BP neural network［J］. China Safety Science Journal， 2022， 32（1）： 27-33 （in Chinese）. | |
| 10 | 任小华， 种兰祥， 杨建锋. 基于FT＿BP神经网络的学业预警模型［J］. 计算机应用研究， 2020， 37（）： 83-85， 97. |
| REN X H， CHONG L X， YANG J F. Academic early warning model based on FT_BP neural network［J］. Application Research of Computers， 2020， 37（S1）： 83-85， 97 （in Chinese）. | |
| 11 | 中国民用航空总局. 循证训练（EBT）实施方法： AC-121-FS-138R1 ［S］. 北京：中国民用航空总局， 2023. |
| Civil Aviation Administration of China. Implementation method of evidence-based training：AC-121-FS-138R1 ［S］. Beijing： Civil Aviation Administration of China， 2023 （in Chinese）. | |
| 12 | 马宝亮. 试飞安全管理体系中的风险管理研究［J］. 中国新技术新产品， 2019（24）： 139-140. |
| MA B L. Research on risk management in flight test safety management system［J］. New Technology & New Products of China， 2019（24）： 139-140 （in Chinese）. | |
| 13 | LYU X T， DING P， LI S Y， et al. Human factors engineering of BCI： An evaluation for satisfaction of BCI based on motor imagery［J］. Cognitive Neurodynamics， 2023， 17（1）： 105-118. |
| 14 | JAFARI ROODBANDI A S， CHOOBINEH A， BARAHMAND N， et al. Research outputs in ergonomics and human factors engineering： A bibliometric and co-word analysis of content and contributions［J］. International Journal of Occupational Safety and Ergonomics： JOSE， 2022， 28（4）： 2010-2021. |
| 15 | 陈浩然， 崔利杰， 任博， 等. 基于STAMP的试飞安全指标体系构建方法［J］. 火力与指挥控制， 2019， 44（2）： 54-59. |
| CHEN H R， CUI L J， REN B， et al. Research on the construction of aircraft test flight safety index based on STAMP［J］. Fire Control & Command Control， 2019， 44（2）： 54-59 （in Chinese）. | |
| 16 | 陈君石， 黄建始. 健康管理师［M］. 北京： 中国协和医科大学出版社， 2007： 347. |
| CHEN J S， HUANG J S. Health management specialist［M］. Beijing： Peking Union Medical College Press， 2007： 347 （in Chinese）. | |
| 17 | CHEN B P， CHEN Y， ZENG G Q， et al. Fractional-order convolutional neural networks with population extremal optimization［J］. Neurocomputing， 2022， 477： 36-45. |
| 18 | SHEIKHI S， KOSTAKOS P. A novel anomaly-based intrusion detection model using PSOGWO-optimized BP neural network and GA-based feature selection［J］. Sensors， 2022， 22（23）： 9318. |
| 19 | SU J Y， CHEN Y， ZHANG D B， et al. Full-parameter identification model based on back propagation algorithm for brushless doubly fed induction generator［J］. IEEE Transactions on Power Electronics， 2020， 35（10）： 9953-9958. |
| 20 | SINGH N， PANDA S P. Heterogeneous computing with graphical processing unit： Improvised back-propagation algorithm for water level prediction［J］. International Journal of Electrical and Computer Engineering （IJECE）， 2022， 12（4）： 4090. |
| 21 | ZHANG Q， WANG J J， ZHANG H， et al. Research on quantitative evaluation method of test flight risk based on fuzzy theory［C］∥ International Conference on Computer Graphics， Artificial Intelligence， and Data Processing （ICCAID 2022）. 2023， 12604： 1114-1122. |
/
| 〈 |
|
〉 |
CJA