《计算机应用》唯一官方网站 ›› 2026, Vol. 46 ›› Issue (3): 1011-1022.DOI: 10.11772/j.issn.1001-9081.2025081052

• 前沿与综合应用 • 上一篇    

基于梯度提升回归树的飞行操作绩效评估方法

魏麟1, 李海敏1(), 叶娅兰2, 邢宇飞3, 陈鹏1   

  1. 1.中国民用航空飞行学院 航空电子电气学院,成都 641419
    2.电子科技大学 计算机科学与工程学院,成都 610054
    3.西藏航空有限公司,成都 610000
  • 收稿日期:2025-09-11 修回日期:2025-10-28 接受日期:2025-10-31 发布日期:2025-11-05 出版日期:2026-03-10
  • 通讯作者: 李海敏
  • 作者简介:魏麟(1972—),男,四川资阳人,教授,硕士,主要研究方向:航空安全管理、航空电子、航空通信
    叶娅兰(1975—),女,四川宜宾人,教授,博士,主要研究方向:心理风险、人工智能
    邢宇飞(1988—),男,陕西西安人,二级飞行员,硕士,主要研究方向:飞行、飞行标准管理
    陈鹏(1997—),男,山西临县人,硕士研究生,主要研究方向:智能感知、自主控制。
  • 基金资助:
    国家自然科学基金资助项目(U2333211)

Flight operation performance evaluation method based on gradient boosting regression tree

Lin WEI1, Haimin LI1(), Yalan YE2, Yufei XING3, Peng CHEN1   

  1. 1.Institute of Electronic and Electrical Engineering,Civil Aviation Flight University of China,Chengdu Sichuan 641419,China
    2.School of Computer Science and Engineering,University of Electronic Science and Technology of China,Chengdu Sichuan 610054,China
    3.Tibet Airlines Company Limited,Chengdu Sichuan 610000,China
  • Received:2025-09-11 Revised:2025-10-28 Accepted:2025-10-31 Online:2025-11-05 Published:2026-03-10
  • Contact: Haimin LI
  • About author:WEI Lin, born in 1972, M. S., professor. His research interests include aviation safety management, avionics, aviation communication.
    YE Yalan, born in 1975, Ph. D., professor. Her research interests include psychological risks, artificial intelligence.
    XING Yufei, born in 1988, M. S., second-grade pilot. His research interests include flight, flight standard management.
    CHEN Peng, born in 1997, M. S. candidate. His research interests include intelligent perception, autonomous control.
  • Supported by:
    National Natural Science Foundation of China(U2333211)

摘要:

针对传统飞行操作绩效评估方法主观性强、参数分析片面和难以全面客观量化等问题,提出一种基于多维度特征解析的梯度提升回归树(MFA-GBRT)方法。该方法通过提取快速存取记录器(QAR)数据的时域和趋势特征,结合改进梯度提升回归树(GBRT)与阈值累积重要性筛选机制,构建覆盖“姿态控制-动力管理-环境响应”的评估指标体系与绩效等级评估模型。模拟机和飞行基地数据上的实验结果表明,该方法评估平均准确率达87.83%,较现有算法LSTM-DNN(Long Short-Term Memory-Deep Neural Network)、曲线相似度和小波分析分别提升了10.78%、6.06%和3.55%;而跨场景验证显示,该方法在三类不同飞行场景中的适配度均达95%以上(高适配)。可见,该方法实现了飞行过程的全流程客观量化评估,为飞行操作绩效评估提供了具备工程实用性的科学方案。

关键词: 快速存取记录器, 飞行操作绩效, 梯度提升, 特征提取, 飞行安全

Abstract:

To address the problem that traditional flight operation performance evaluation methods are highly subjective, analyze parameters one-sidedly, and cannot be quantified comprehensively and objectively, a Multi-dimensional Feature Analysis based Gradient Boosting Regression Tree (MFA-GBRT) method was proposed. In the method, time-domain and trend features of Quick Access Recorder (QAR) data were extracted, and an improved Gradient Boosting Regression Tree (GBRT) was combined with a threshold cumulative importance filtering mechanism, an evaluation index system covering “attitude control-power management-environmental response” and a performance level evaluation model were constructed. Experimental results on simulator and flight base data show that the average evaluation accuracy of the proposed method reaches 87.83%, which is 10.78%, 6.06% and 3.55% higher than those of the existing methods Long Short-Term Memory-Deep Neural Network (LSTM-DNN), curve similarity method and wavelet analysis, respectively. Cross-scenario validation show that the method has adaptability over 95% (high adaptability) in three different flight scenarios. It can be seen that the method realizes full-process objective quantitative evaluation of the flight process and provides a scientific scheme with engineering practicability for flight operation performance evaluation.

Key words: Quick Access Recorder (QAR), flight operation performance, gradient boosting, feature extraction, flight safety

中图分类号: