| 0 | 0 | 2 |
| 下载次数 | 被引频次 | 阅读次数 |
目的 以飞行员飞行训练为背景，通过连续监测飞行中生理数据，结合主观操纵负荷评价量表，构建以客观生理数据为输入的飞行员操纵负荷评价模型，并验证模型判别结果与主观评价结果的一致性。方法 2024年3月于某单位选取8名飞行员，在飞行中开展生理监测，监测脉搏波指标，采集26架次飞行中数据。飞行员飞行后填写主观操纵负荷评价量表，实现飞行过程中的操纵负荷评价。结果 采用决策树算法建立飞行员操纵负荷评估模型，低负荷的准确率为90.9%，高负荷的准确率为93.3%，总体操纵负荷的准确率为92.1%。结论 飞行员操纵负荷评估模型，能够准确评估飞行过程中的负荷程度，为飞行人员飞行训练航卫保障提供参考依据。
Abstract：Objective To develop an objective pilot control workload assessment model using physiological data monitored during flight training, combined with subjective workload evaluation scales, and the consistency between model predictions and subjective assessments was also verified. Methods In March 2024, eight pilots were recruited from a military unit to participate in the study. Physiological parameters(pulse wave indicators) were continuously monitored across 26 flight sessions. After each flight, pilots completed a subjective control load evaluation questionnaire to quantify their perceived workload. Results A decision tree algorithm was used to construct the pilot control load assessment model, which achieved an accuracy of 90.9% for low workload, 93.3% for high workload, and an overall accuracy of 92.1%. Conclusions The proposed pilot control workload assessment model can accurately evaluate workload levels during flight sessions, which provides a scientific reference for aviation medical support in flight training.
[1]HEBBAR PA, VINOD S, SHAH AK, et al. Cognitive load estimation in VR flight simulator[J]. J Eye Mov Res, 2023,15(3):10. DOI:10.16910/jemr.15.3.11.
[2]KOSKELO J, LEHMUSAHO A, LAITINEN TP, et al. Cardiac autonomic responses in relation to cognitive workload during simulated military flight[J]. Appl Ergon, 2024, 121:104370. DOI:10.1016/j.apergo.2024.104370.
[3]LI W, LI R, XIE X, et al. Evaluating mental workload during multitasking in simulated flight[J]. Brain Behav, 2022, 12(4):e2489.DOI:10.1002/brb3.2489.
[4]阮森,林贝,朱煜阳,等.不同脑力负荷模拟飞行任务脑电功率谱研究[D].保定:河北大学, 2022. DOI:10.7644/j.issn.1674-9960.2022.07.004.
[5]李文斌,康阳,谢小萍,等.基于脑电微状态分析的模拟飞行多任务脑力负荷敏感性研究[J].载人航天, 2022, 28(1):55-62. DOI:10.3969/j.issn.1674-5825.2022.01.008.
[6]汪磊,张之洋,谭维,等. fNIRS技术在飞行员脑力负荷测量中的应用[J].综合运输, 2024, 46(2):91-100. DOI:10.20164/j.cnki.cn11-1197/u.2024.02.015.
[7]何雪丽,王黎静,湛希,等.飞行员工作负荷定量实时预测模型[J/OL].北京航空航天大学学报, 2024.(2024-09-04)[2025-06-13].https://doi.org/10.13700/j.bh.1001-5965.2024.0279. DOI:10.13700/j.bh.1001-5965.2024.0279.
[8]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.
[9]曹征涛,熊瑾乐,梁学宇,等.基于心率变异性的长航时模拟飞行疲劳评估[J].空军军医大学学报, 2024(2):045. DOI:10.13276/j.issn.2097-1656.2024.02.011.
[10]鞠博文,程珊,丛林,等.实际工作背景下脑力与体力因素叠加效应对认知负荷的影响[J].空军航空医学, 2024, 41(3):193-198.DOI:10.3969/j.issn.2097-1753.2024.03.001.
[11]晋良海,李宬.高处作业人员心理负荷的SWAT量表主观评定方法研究[J].安全与环境工程, 2015, 22(3):6. DOI:10.13578/j.cnki.issn.1671-1556.2015.03.014.
[12]刘维平,赵凯旋,聂俊峰,等.基于任务的乘员脑力负荷典型主观评价方法[J].科学技术与工程, 2018, 18(14):131-135.DOI:10.3969/j.issn.1671-1815.2018.14.023.
[13]张静,李化奇,陈玲艳.基于决策树算法的生理特征数据分析方法研究[J].电子设计工程, 2021, 29(2):21-24. DOI:10.14022/j.issn1674-6236.2021.02.005.
[14]ANTOINE M, ABDESSALEM HB, FRASSON C. Cognitive workload assessment of aircraft pilots[J]. J Behav Brain Sci, 2022,12(10):474-484. DOI:10.4236/jbbs.2022.1210027.
[15]MOHANAVELU K, POONGUZHALI S, JANANI A, et al. Machine learning-based approach for identifying mental workload of pilots[J]. Biomed Signal Proces, 2022, 75(5):9. DOI:10.1016/j.bspc.2022.103623.
[16]WANG P, HOUGHTON R, MAJUMDAR A. Detecting and predicting pilot mental workload using heart rate variability:a systematic review[J]. Sensors(Basel), 2024, 24(12):3723. DOI:10.3390/s24123723.
基本信息:
DOI：10.16289/j.cnki.1002-0837.2026.01006
中图分类号:V323
引用信息:
[1]尚腊梅,曹征涛,周玉彬,等.飞行员飞行训练过程中操纵负荷评估模型研究[J].航天医学与医学工程,2026,37(01):30-33.DOI:10.16289/j.cnki.1002-0837.2026.01006.