Research on Digital Simulation Method for Cognitive Load Evaluation of pilots

doi:10.16182/j.issn1004731x.joss.25-0311

Abstract

Abstract:

The operator's cognitive load constitutes a critical determinant of task performance. Pilots, as the primary operators of aircraft, must face an overwhelming volume of information during complex missions, which significantly heightens the risk of cognitive overload and operational errors. Evaluating cognitive load during tasks helps reduce human errors and improve system safety by optimizing design schemes. A simulation model was established to dynamically predict the pilots' cognitive load during tasks for multi-task scenarios. Based on the multiple resource theory, a method for quantifying cognitive load in multi-task conditions was established. By considering cognitive capacity, task time constraints, task priority, and temporal randomness, a dynamic model of task process was constructed based on the random-time extended weighted Petri net. Based on the experimental data, cognitive load values were predicted, and the effectiveness of the cognitive load evaluation model was verified. The results indicate that the sensitive physiological parameter is significantly correlated with predicted values of cognitive load.

Key words: cognitive load, multiple resource theory, multi-task scenario, Petri net, dynamic model of task process

CLC Number:

TP391.9

Fan Zeng, He Mingjun, Xing Xiangyu. Research on Digital Simulation Method for Cognitive Load Evaluation of pilots[J]. Journal of System Simulation, 2025, 37(8): 1921-1932.

Figures/Tables 13

Fig. 1

Table 1

Fig. 2

Fig. 3

Fig. 4

Fig. 5

Fig. 6

Table 2

Table 3

Experimental measurement data

测量数据

指标

绩效测量

TRACK任务：目标圆心与中心距离的均方根偏差(RMSD)

其余任务：反应时间(RT)和正确率

主观测量

NASA-TLX量表主观认知负荷

资源需求水平

生理测量

眼动数据(注视点、注视时间)

脑电数据( $θ$ [4~7 Hz]、 $α$ [8~12 Hz]频带功率)

Table 3

Table 4

Fig. 7

Fig. 8

Table 5

References 19

[1]	Naval Institute Staff U.S.. Report of National Commission on Military Aviation Safety on Aviation Mishaps from 2013 to 2020[EB/OL]. (2020-12-03) [2025-04-08]. .
[2]	Sweller J. Cognitive Load During Problem Solving: Effects on Learning[J]. Cognitive Science, 1988, 12(2): 257-285.
[3]	余琦玮, 唐为昊, 耿洁. 面向复杂装配任务的脑力负荷综合评估方法[J]. 工业工程, 2024, 27(2): 67-73, 97.
	Yu Qiwei, Tang Weihao, Geng Jie. A Synthetic Evaluation Method for Mental Workload in Complex Assembly Task[J]. Industrial Engineering Journal, 2024, 27(2): 67-73, 97.
[4]	李文斌, 谢小萍, 常耀明. 任务绩效在脑力负荷测量中的理论基础与应用[J]. 人类工效学, 2020, 26(1): 75-79.
[5]	钱锋, 贺强. 航空器孔探人员脑力负荷预测[J]. 机械设计与制造, 2024(5): 35-40.
	Qian Feng, He Qiang. Workload Prediction of Aircraft Borescope Inspection[J]. Machinery Design & Manufacture, 2024(5): 35-40.
[6]	Mansikka Heikki, Virtanen Kai, Harris D. Comparison of NASA-TLX Scale, Modified Cooper-harper Scale and Mean Inter-beat Interval as Measures of Pilot Mental Workload During Simulated Flight Tasks[J]. Ergonomics, 2019, 62(2): 246-254.
[7]	汪磊, 张之洋, 邵铿睿, 等. 模拟SPO情境中的飞行员脑力负荷测量与分析[J]. 中国安全生产科学技术, 2022, 18(12): 26-32.
	Wang Lei, Zhang Zhiyang, Shao Kengrui, et al. Measurement and Analysis on Mental Workload of Pilot in Simulated SPO Scenario[J]. Journal of Safety Science and Technology, 2022, 18(12): 26-32.
[8]	Yin Zhong, Zhang Jianhua. Cross-session Classification of Mental Workload Levels Using EEG and an Adaptive Deep Learning Model[J]. Biomedical Signal Processing and Control, 2017, 33: 30-47.
[9]	Wu Qi, Xiong Pengwen, Tang Zhiri, et al. Detecting Dynamic Behavior of Brain Fatigue Through 3-D-CNN-LSTM[J]. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2022, 52(1): 90-100.
[10]	刘承平, 肖旭, 赵竞全. 基于认知过程的飞行员脑力负荷动态预测[J]. 北京航空航天大学学报, 2023, 49(11): 2921-2928.
	Liu Chengping, Xiao Xu, Zhao Jingquan. Pilots' Mental Workload Dynamic Prediction Based on Cognitive Process[J]. Journal of Beijing University of Aeronautics and Astronautics, 2023, 49(11): 2921-2928.
[11]	陆旭, 王天博, 庞丽萍, 等. 执飞任务中剩余脑力负荷量化评估模型[J]. 北京航空航天大学学报, 2023, 49(5): 1184-1192.
	Lu Xu, Wang Tianbo, Pang Liping, et al. Quantitative Evaluation Model of Surplus Mental Workload in Flight Task[J]. Journal of Beijing University of Aeronautics and Astronautics, 2023, 49(5): 1184-1192.
[12]	Wickens C D. Multiple Resources and Performance Prediction[J]. Theoretical Issues in Ergonomics Science, 2002, 3(2): 159-177.
[13]	王洁, 方卫宁, 李广燕. 基于多资源理论的脑力负荷评价方法[J]. 北京交通大学学报, 2010, 34(6): 107-110.
	Wang Jie, Fang Weining, Li Guangyan. Mental Workload Evaluation Method Based on Multi-resource Theory Model[J]. Journal of Beijing Jiaotong University, 2010, 34(6): 107-110.
[14]	Wang Peng, Fang Weining, Guo Beiyuan. A Measure of Mental Workload During Multitasking: Using Performance-based Timed Petri Nets[J]. International Journal of Industrial Ergonomics, 2020, 75: 102877.
[15]	Wang Peng, Fang Weining, Guo Beiyuan. Mental Workload Evaluation and Its Application in Train Driving Multitasking Scheduling: A Timed Petri Net-based Model[J]. Cognition, Technology & Work, 2021, 23(2): 299-313.
[16]	Horrey W J, Wickens C D. Multiple Resource Modeling of Task Interference in Vehicle Control, Hazard Awareness and In-vehicle Task Performance[C]//Proceedings of the Second International Driving Symposium on Human Factors in Driver Assessment, Training, and Vehicle Design. Iowa City: Human Factors Research Program, 2003: 7-12.
[17]	Liu Shijing, Nam C S. Quantitative Modeling of User Performance in Multitasking Environments[J]. Computers in Human Behavior, 2018, 84: 130-140.
[18]	So W K Y, Wong S W H, Mak J N, et al. An Evaluation of Mental Workload with Frontal EEG[J]. PLoS One, 2017, 12(4): e0174949.
[19]	Brookings J B, Wilson G F, Swain C R. Psychophysiological Responses to Changes in Workload During Simulated Air Traffic Control[J]. Biological Psychology, 1996, 42(3): 361-377.

			任务2
			知觉				认知		反应
			VF	VA	AS	AV	CS	CV	RS	RV
任务1	知觉	VF	0.8	0.6	0.6	0.4	0.7	0.5	0.4	0.2
		VA		0.8	0.4	0.6	0.5	0.7	0.2	0.4
		AS			0.8	0.4	0.7	0.5	0.4	0.2
		AV				0.8	0.5	0.7	0.2	0.4
	认知	CS					0.8	0.6	0.6	0.4
	认知	CV						0.8	0.4	0.6
	反应	RS							0.8	0.6
	反应	RV								1.0

任务编号	子任务
1*	TRACK
2*	SYSMON
3*	COMM
4*	RESMAN
1	TRACK	SYSMON
2	TRACK	COMM
3	TRACK	RESMAN
4	TRACK	SYSMON	COMM
5	TRACK	SYSMON	RESMAN
6	TRACK	COMM	RESMAN

子任务绩效	任务	显著性
SYSMON	1&4	p = 0.031*
COMM	2&4	p = 0.645
RESMAN	3&6	p = 0.005**
COMM	2&6	p = 0.866
RESMAN	1&5	p = 0.097
SYSMON	3&5	p = 0.258

分析阶段	被试	CCPZ	PO1
全任务过程	被试1	0.04	0.13*
	被试5	0.29**	0.29**
	被试6	0.21**	0.16**
	被试7	0.03	0.16**
	所有被试均值	0.14**	0.28**
高负荷阶段	被试1	0.19	0.44*
	被试3	0.64**	0.51**
	被试4	0.13	0.40*
	被试7	0.22	0.43*
	所有被试均值	0.12	0.40*