基于BP神经网络的试飞训练安全性量化模型  

BP neural network⁃based quantitative classification model for safety in experimental flight training

作　　者：马菲 张琼 赖培军 岳一笛 MA Fei;ZHANG Qiong;LAI Peijun;YUE Yidi(Flight Test Center,Commercial Aircraft Corporation of China,Shanghai 200232,China;School of Aeronautics,Northwestern Polytechnical University,Xi’an 710072,China;College of Civil Aviation,Nanjing University of Aeronautics and Astronautics,Nanjing 210016,China)

机构地区：[1]中国商飞民用飞机试飞中心,上海200232 [2]西北工业大学航空学院,西安710072 [3]南京航空航天大学民航学院,南京210016

出　　处：《航空学报》2024年第5期409-422,共14页Acta Aeronautica et Astronautica Sinica

基　　金：国家级项目。

摘　　要：为提升试飞员在航空试验飞行过程中的飞行安全、降低试验飞行的风险等级,研究基于BP神经网络的试验飞行训练安全性分级量化分析模型。以人因工程的人、机、环为切入,分析试验飞行训练过程中影响试飞安全的因素,并选取人、试飞训练科目及环境三部分重要因素,建立试验飞行训练过程中的安全性分级量化分析指标体系。经人因工程指标量化处理后,由于融合的数据类型相似度较低,因此采用BP神经网络构建试验飞行训练安全性分级量化分析模型,经模型训练、测试后,输出试验飞行训练的安全性分级量化等级。利用定制的接触式采集设备和非接触式面部识别系统,采集试飞员执行试飞科目训练时身体节律数据,分析训练过程中科目复杂度和难度对试飞员心理特征和生理特征的影响,从而建立量化指标和预警指标,以此优化试验飞行训练课程、提高训练品质,保障试飞安全。试验表明,该模型所得试验飞行训练过程中的安全性分级量化模型输出偏差小于2%,模型预测结果与训练过程中实际风险等级基本吻合,可有效地用于试飞训练过程中风险预警,提高试飞员训练品质,为实际试飞安全提供保障。To enhance the safety of test pilots during aviation experimental flights and reduce the risk level of experi⁃mental 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 condi⁃tions.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 experi⁃mental 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 sys⁃tem,the physiological rhythm data of test pilots during the execution of experimental flight training subjects are col⁃lected.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 indica⁃tors 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 classifica⁃tion model for safety in the experimental flight training process is less than 2%.The model’s predicted results closely align with the actual ris

关 键 词：人因工程 BP神经网络 风险预警 试验飞行训练过程 分级量化 

分 类 号：V217[航空宇航科学与技术—航空宇航推进理论与工程]