中国安全科学学报 ›› 2026, Vol. 36 ›› Issue (8): 124-132.doi: 10.16265/j.cnki.issn1003-3033.2026.08.0848

• 安全技术与工程 • 上一篇    下一篇

数据不均衡下教练机致命事故识别与分析

张庆峰1(), 曹宇飞1, 周悦1,**(), 付川云2   

  1. 1 中国民用航空飞行学院 飞行技术学院, 四川 广汉 618307
    2 哈尔滨工业大学 交通科学与工程学院, 黑龙江 哈尔滨 150090
  • 收稿日期:2026-03-15 修回日期:2026-05-21 出版日期:2026-08-28
  • 通信作者:
    **周悦(1992—),男,四川成都人,博士,讲师,主要从事民航安全与事故分析、空中特情处置及飞行员生理特征分析方面的研究。E-mail:
  • 作者简介:

    张庆峰 (1982—),男,四川成都人,硕士,副教授,主要从事航空安全、工程力学及智能材料与结构方面的研究。E-mail:

    付川云 副教授

  • 基金资助:
    国产民机飞行与运行支持四川省工程研究中心项目(MJCYZY202504); 四川省民航飞行技术与飞行安全工程技术研究中心项目(GY2024-07B); 中央高校基本科研业务费资助项目(25CAFUC03006); 中央高校基本科研业务费资助项目(25CAFUC04004)

Identification and analysis of fatal accidents of training aircraft under uneven distribution of accident types

Zhang Qingfeng1(), Cao Yufei1, Zhou Yue1,**(), Fu Chuanyun2   

  1. 1 Flight Technology College, Civil Aviation Flight University of China, Guanghan Sichuan 618307, China
    2 School of Transportation Science and Engineering, Harbin Institute of Technology, Harbin Heilongjiang 150090, China
  • Received:2026-03-15 Revised:2026-05-21 Published:2026-08-28

摘要:

为降低教练机飞行训练伤亡率,明确教练机事故致命性机制及影响因素,首先,采用美国国家运输安全委员会(NTSB)通用航空教练机事故数据,提取时间、飞行、飞行员、飞机运营、气象及机场6大维度变量;其次,通过合成少数类过采样技术(SMOTE)、自适应合成采样(ADASYN)等重采样技术处理数据不均衡问题;最后,训练多类可解释机器学习模型,解析事故致因及致死事故影响因素。结果表明:结合边界线SMOTE(采样比例0.12)的轻量级梯度提升机(LightGBM)模型在事故致命性识别中性能最优,准确率为96.04%,宏F1为88.19%;在特征影响因素中,事故出现在飞行-机动阶段、飞行-起飞阶段,以及出现飞行-空中失去控制事件与致命事故的发生正相关,飞行-着陆阶段与之负相关,同时飞行员年龄>65岁产生混合影响。

关键词: 数据不均衡, 教练机, 致命事故, 机器学习, 航空事故, 轻量级梯度提升机(LightGBM)模型, 夏普利加性解释(SHAP)

Abstract:

To clarify the lethality mechanisms of trainer aircraft accidents with significantly imbalanced accident data, the influencing factors of their lethality were analyzed. The accident data for general aviation trainer aircraft from the National Transportation Safety Board (NTSB) were utilized. Six dimensions of variables, namely time, flight, pilot, aircraft operation, meteorology, and airport, were extracted. Given that fatal accidents accounted for 9.66% of the data, a sample imbalance existed. Resampling techniques, including the Synthetic Minority Over-sampling Technique (SMOTE) and Adaptive Synthetic (ADASYN) sampling, were employed to address this issue. Multiple interpretable machine learning models were subsequently trained to analyze accident causes and fatal accident influencing factors. The results indicate that the LightGBM model combined with Borderline-SMOTE (synthetic sample ratio 0.12) achieves the optimal performance in predicting accident fatality. Its accuracy is 96.04%, and its macro-F1 score is 88.19%. Among the characteristic influencing factors, accidents occurring in the flight-maneuvering phase, the flight-takeoff phase, and in-flight loss-of-control events are positively correlated with fatal accidents. The flight-landing phase is negatively correlated with fatal accidents. Pilots aged over 65 produces a mixed effect. This study, through interpretable machine learning models, reveals the key influencing factors for the fatality of trainer aircraft accidents. It provides an empirical basis for understanding the accident mechanism.

Key words: data imbalance, trainer aircraft, fatal accident, machine learning, aviation accidents, light gradient boosting machine (LightGBM) model, Shapley additive explanations (SHAP)

中图分类号: