《计算机应用》唯一官方网站 ›› 2026, Vol. 46 ›› Issue (10): 3161-3170.DOI: 10.11772/j.issn.1001-9081.2025080942

• 人工智能 • 上一篇    

基于CTrans-ATGCN的航班地面保障里程碑事件预测

冯霞1,2(), 王琦1,3, 张明泽1,3, 左海超1,3, 王国钰4,5   

  1. 1.中国民航大学 民航智慧机场理论与系统重点实验室,天津 300300
    2.中国民航大学 科技创新研究院,天津 300300
    3.中国民航大学 计算机与人工智能学院,天津 300300
    4.北京交通大学 电子信息工程学院,北京 100044
    5.华为技术有限公司 交通智慧化军团,广东 深圳 518129
  • 收稿日期:2025-08-18 修回日期:2025-08-29 接受日期:2025-09-15 发布日期:2026-10-21 出版日期:2026-10-10
  • 通讯作者: 冯霞
  • 作者简介:王琦(2000—),男,黑龙江齐齐哈尔人,硕士,主要研究方向:航空大数据智能、航班地面保障时间预测
    张明泽(1999—),男,山东泰安人,硕士研究生,主要研究方向:机场群时隙分配优化
    左海超(1986—),男,河南新郑人,博士研究生,主要研究方向:民航智能信息处理、智慧机场
    王国钰(1977—),男,山西大同人,博士研究生,主要研究方向:交通行业数智化、无线通信。
  • 基金资助:
    国家自然科学基金民航联合基金重点项目(U2333206);中国民航大学研究生科技创新项目(2023YJSKC05004)

Flight ground service milestone event prediction based on CTrans-ATGCN

Xia FENG1,2(), Qi WANG1,3, Mingze ZHANG1,3, Haichao ZUO1,3, Guoyu WANG4,5   

  1. 1.Key Laboratory of Civil Aviation Smart Airport Theory and System,Civil Aviation University of China,Tianjin 300300,China
    2.Institute of Science and Technology Innovation,Civil Aviation University of China,Tianjin 300300,China
    3.School of Computer Science and Artificial Intelligence,Civil Aviation University of China,Tianjin 300300,China
    4.School of Electronic and Information Engineering,Beijing Jiaotong University,Beijing 100044,China
    5.Transportation Intelligence Corps,Huawei Technologies Company Limited,Shenzhen Guangdong 518129,China
  • Received:2025-08-18 Revised:2025-08-29 Accepted:2025-09-15 Online:2026-10-21 Published:2026-10-10
  • Contact: Xia FENG
  • About author:WANG Qi, born in 2000, M. S. His research interests include big data intelligence in civil aviation, flight ground service time prediction.
    ZHANG Mingze, born in 1999, M. S. candidate. His research interests include airport network slot allocation optimization.
    ZUO Haichao, born in 1986, Ph. D. candidate. His research interests include intelligent information processing in civil aviation, smart airport.
    WANG Guoyu, born in 1977, Ph. D. candidate. His research interests include digitalization and intelligence in transportation industry, wireless communication.
  • Supported by:
    Key Project of Civil Aviation Joint Fund of National Natural Science Foundation of China(U2333206);Postgraduate Scientific Research Innovation Project of Civil Aviation University of China(2023YJSKC05004)

摘要:

针对航班地面保障里程碑事件预测面临的数据缺失严重、影响因素不确定和预测精度不高等问题,提出一种航班地面保障里程碑事件预测框架CTrans-ATGCN,包括缺失数据填补和里程碑事件预测两大核心组件。该框架基于Transformer架构,引入卷积层提取航班地面保障里程碑事件数据中蕴含的时序和拓扑特征,采用自注意力机制建模不同里程碑事件之间潜在的全局依赖关系,构建融合卷积自注意力机制的航班地面保障数据填补方法CTrans(Convolutional Transformer)。在此基础上,构建里程碑事件预测方法——基于注意力的时序图卷积网络(ATGCN)。该方法利用时序图卷积网络(T-GCN)捕捉里程碑事件的历史数据中蕴含的时空依赖关系,并结合注意力机制与评分函数动态地调整不同里程碑事件节点之间的权重,从而实现对地面保障里程碑事件的高精度预测。在华北地区某机场2023年真实数据集上的实验结果表明,所提填补方法在缺失率为70%的非随机缺失场景下,相较于次优模型GraphSAGE(Graph Sample and AggreGatE)的平均绝对误差(MAE)降低了约14.91%;而在低缺失率数据集上,所提“填补+预测”方法取得了与滑动双向图卷积神经网络模型(SBDGCNM)相当的预测效果;在缺失率为70%的数据集上,CTrans-ATGCN的MAE和均方根误差(RMSE)分别为14.76和18.42,优于所有基准方法。可见,该框架为解决数据缺失下的航班地面保障预测问题提供了有效方法,为地勤高效调度人员与设备提供了可靠支持。

关键词: 航班地面保障, 图卷积网络, 时间序列填补, 里程碑事件预测, Transformer模型, 注意力机制

Abstract:

To address the challenges of severe data missingness, high uncertainty in influencing factors, and limited prediction accuracy in flight ground service milestone event prediction, a flight ground service milestone event prediction framework named CTrans-ATGCN was proposed, including two core components: missing data imputation and milestone event prediction. First, based on the Transformer architecture, a convolutional layer was introduced to extract the temporal and topological features in flight ground service milestone event data, and a self-attention mechanism was employed to model potential global dependencies among different milestone events, thereby constructing CTrans (Convolutional Transformer), a method for flight ground service data imputation that integrates convolutional self-attention mechanism. On this basis, a milestone event prediction method, Attention-based Temporal Graph Convolutional Network (ATGCN), was constructed. In this method, a Temporal Graph Convolutional Network (T-GCN) was utilized to capture spatio-temporal dependencies in historical milestone event data, and by combining an attention mechanism with a scoring function, the weights among different milestone event nodes were adjusted dynamically, so as to achieve high-precision prediction for ground service milestone events. Experimental results on a 2023 real-world dataset from an airport in North China show that in a non-random missing scenario with a 70% missing rate, the proposed imputation method reduces the Mean Absolute Error (MAE) by approximately 14.91% compared to the suboptimal model GraphSAGE (Graph Sample and AggreGatE); on low-missing-rate datasets, the proposed “imputation + prediction” method achieves prediction performance similar to that of Sliding Bi-Directional Graph Convolutional Neural network Model (SBDGCNM); on datasets with 70% missing rate, CTrans-ATGCN achieves the MAE and Root Mean Square Error (RMSE) of 14.76 and 18.42, respectively, outperforming all baseline methods. It can be seen that this framework provides an effective method for flight ground service prediction under missing data, and offers reliable support for efficient scheduling of ground personnel and equipment.

Key words: flight ground service, Graph Convolutional Network (GCN), time series imputation, milestone event prediction, Transformer model, attention mechanism

中图分类号: