| 0 | 0 | 0 |
| 下载次数 | 被引频次 | 阅读次数 |
为满足民航法规中关于机组疲劳管理的要求，以心率变异性作为疲劳评价指标，设计了基于双向长短期记忆网络-多头注意力(BiLSTM-MHA)机制的预测模型，利用重叠窗口采样法提取飞行员心率变异性指标参数，将提取的数据作为模型输入进行预测。以决定系数R2、平均绝对误差SMAE、均方根误差SRMSE作为模型的性能评价标准，对比验证其他3种长短期记忆网络模型的预测准确性。测试结果表明，BiLSTM-MHA对心率变异性指标参数的预测均优于对比模型，能够为飞行疲劳的提前干预提供重要依据，对于提升航空安全管理水平具有积极意义。
Abstract：To meet the requirements of civil aviation regulations regarding crew fatigue management, a prediction model based on the bidirectional long short-term memory with multi-head attention(BiLSTM-MHA) was designed using heart rate variability(HRV) as the fatigue assessment metric. Overlapping window sampling was used to extract HRV parameter features from pilots' physiological data, which were then utilized as model inputs. Model performance was evaluated using the coefficient of determination(R2), mean absolute error(SAME), and root mean square error(SRMSE). The predictive accuracy of the BiLSTM-MHA model was systematically compared against three other LSTM-based models. Test results showed that the BiLSTM-MHA model consistently outperformed the comparative models in predicting HRV parameters, providing a critical foundation for early intervention in flight fatigue and offering significant potential to enhance aviation safety management.
[1]张荣,梁馨月.航空人员疲劳检测方法研究[J].计算机工程与应用, 2024, 60(20):84-95. DOI:10.3778/j.issn.1002-8331.2403-0135.
[2]范晓丽,郭华,邵舒羽,等.飞行员脑力疲劳评价方法的研究与进展[J].人类工效学, 2024, 30(4):80-86. DOI:10.13837/j.issn.1006-8309.2024.04.0013.
[3]HAMANN A, CARSTENGERDES N. Assessing the development of mental fatigue during simulated flights with concurrent EEG-fNIRS measurement[J]. Sci Rep, 2023, 13(1):4738. DOI:10.1038/s41598-023-31264-w.
[4]DRAICCHIO F, CHINI G, SILVETTI A, et al. Neck and shoulder muscle fatigue in high performance aircrafts pilots:a case study[C].International Conference on Applied Human Factors and Ergonomics,2019. DOI:10.1007/978-3-319-93885-1_5.
[5]HANAKOVA L, SOCHA V, SOCHA L, et al. The influence of fatigue on psychophysiological indicators during 24hours testing of pilots[C].2019 IEEE 17th World Symposium on Applied Machine Intelligence and Informatics, 2019. DOI:10.1109/SAMI.2019.8782724.
[6]NAEERI S, MANDAL S, KANG Z. Analyzing pilots’ fatigue for prolonged flight missions:multimodal analysis approach using vigilance test and eye tracking[C]. Proceedings of the Human F a c t o r s a n d E rg o n o m i c s S o c i e t y A n n u a l M e e t i n g , 2 0 1 9.DOI:10.1177/1071181319631092.
[7]段亚,冯月,彭冉,等.面向飞行作业人员的实时疲劳监测模型研究[J].飞行力学, 2024, 42(2):68-74. DOI:10.13645/j.cnki.f.d.20240205.001.
[8]中国民用航空局. CCAR121部合格证持有人的疲劳管理要求:AC-121-FS-014R1[S/OL].(2024-03-01). https://www.caac.gov.cn/XXGK/XXGK/GFXWJ/202403/P020240311595553835476.pdf.
[9]赵小静,路海月,王梦悦,等.基于心率变异性的脑力疲劳检测[J].中国医学物理学杂志, 2018, 35(5):592-597. DOI:10.3969/j.issn.1005-202X.2018.05.017.
[10]张宁宁,陈飒.基于心率变异性的飞行员脑力负荷特征[J].科学技术与工程, 2024, 24(13):5634-5641. DOI:10.12404/j.issn.1671-1815.2302452.
[11]王步青,王民,刘洪运,等.基于心率变异性与精神负荷关系的研究[J].中国医疗设备, 2017, 32(6):36-38. DOI:10.3969/j.issn.1674-1633.2017.06.010.
[12]汪磊,郑竹寒,张之洋.基于警觉性的疲劳程度自测系统研究[J].航天医学与医学工程, 2021, 34(5):361-366. DOI:10.16289/j.cnki.1002-0837.2021.05.003.
[13]HALOMOAN J, RAMLI K, SUDIANA D, et al. A new ECG data processing approach to developing an accurate driving fatigue detection framework with heart rate variability analysis and ensemble learning[J]. Information, 2023, 14(4):210. DOI:10.3390/info14040210.
[14]PAVLATOS C, MAKRIS E, FOTIS G, et al. Enhancing electrical load prediction using a bidirectional LSTM neural network[J].Electronics, 2023, 12(22):4652. DOI:10.3390/electronics12224652.
[15]CHAUDHARI S, MITHAL V, POLATKAN G, et al. An attentive survey of attention models[J]. ACM T Intel Syst Tec, 2021, 12(5):1-32.DOI:10.1145/3465055.
[16]AHMADZADEH E, KIM H, JEONG O, et al. A deep bidirectional LSTM-GRU network model for automated ciphertext classification[J]. IEEE Access, 2022, 10:3228-3237. DOI:10.1109/ACCESS.2022.3140342.
[17]张伟,常本强,杨旭,等.基于贝叶斯优化LSTM神经网络的飞机货舱火源定位[J/OL].北京航空航天大学学报, 2025, 51(9):2979-2986. DOI:10.13700/j.bh.1001-5965.2023.0482.
基本信息:
DOI：10.16289/j.cnki.1002-0837.2026.01008
中图分类号:TP183;V328
引用信息:
[1]廖文宇,李立民,潘友彬,等.基于BiLSTM-MHA的飞行员心率变异性预测方法研究[J].航天医学与医学工程,2026,37(01):39-44.DOI:10.16289/j.cnki.1002-0837.2026.01008.
基金信息:
民航飞行技术与飞行安全重点实验室飞行技术专题项目（FZ2022ZX47）; 高校基本科研业务费资助项目（25CAFUC03096）; 四川省民航飞行技术与飞行安全工程技术研究中心项目（GY2025-43E）