The issue of over-limit during passenger aircraft flights has drawn increasing attention in civil aviation due to its potential safety risks. To address this issue, real-time automated warning systems are essential. In this study, a real-time warning model for civil aviation over-limit is proposed based on QAR data monitoring. Firstly, highly correlated attributes to over-limit are extracted from a vast QAR dataset using the Spearman rank correlation coefficient. Because flight over-limit poses a binary classification problem with unbalanced samples, this paper incorporates cost-sensitive learning in the LSTM model. Finally, the time step length, number of LSTM cells, and learning rate in the LSTM model are optimized using a grid search approach. The model is trained on a real dataset, and its performance is evaluated on a validation set. The experimental results show that the proposed model achieves an F1 score of 0.991 and an accuracy of 0.978, indicating its effectiveness in real-time warning of civil aviation over-limit.

翻译：民航客机飞行过程中的超限问题因其潜在的安全风险而日益受到关注。为解决该问题，实时自动化预警系统至关重要。本研究基于QAR数据监测，提出了一种民航超限实时预警模型。首先，利用斯皮尔曼秩相关系数从海量QAR数据集中提取与超限高度相关的属性。由于飞行超限属于样本不平衡的二分类问题，本文在LSTM模型中引入了代价敏感学习。最后，采用网格搜索方法对LSTM模型中的时间步长、LSTM单元数及学习率进行优化。该模型基于真实数据集进行训练，并在验证集上评估其性能。实验结果表明，所提模型的F1分数达0.991，准确率达0.978，验证了其在民航超限实时预警中的有效性。