认知网络模型在空速不可靠人机交互仿真中的应用  

Application of cognitive network model in unreliable airspeed human-computer interaction simulation

作　　者：汪磊 栾昊 杨忠昌 WANG Lei;LUAN Hao;YANG Zhongchang(School of Safety Science and Engineering,Civil Aviation University of China,Tianjin 300300,China)

机构地区：[1]中国民航大学安全科学与工程学院,天津300300

出　　处：《安全与环境学报》2025年第2期572-581,共10页Journal of Safety and Environment

摘　　要：为探索民机驾驶舱人机交互典型场景中人为差错发生的认知层面原因,运用人的排队网络信息加工模型(Queuing Network-Model Human Processor, QN-MHP)和人因可靠性方法对空速不可靠场景下的飞行员行为进行仿真研究。首先,通过设计任务及场景进行任务建模;然后,对模型中表示各脑区功能服务器的处理时间、处理容量及实体处理路径与差错概率赋值,进行24次仿真模拟;最后,通过设计模拟飞行试验,验证QN-MHP模型在民机驾驶舱人机交互研究中的可行性。结果表明,在空客A320机型空速不可靠处置任务中,飞行员在处置路径上易发生人为差错,在故障的识别、判断等关键节点也有少数差错发生,且任务过程中飞行员眼部利用率较高。研究表明,飞行员过高的用眼负荷是导致驾驶舱人机交互失效的原因之一,在未来驾驶舱人机交互流程设计及飞行训练中应予以重点关注。To explore the cognitive-level reasons for human errors in typical human-computer interaction scenarios in civil aircraft cockpits and verify the feasibility of the simulation model,this study employs the Queuing Network-Model Human Processor(QN MHP)model and human reliability methods to model and simulate pilot behavior in scenarios of unreliable airspeed.First,according to the design task and scene,the conditions to be met are selected,the event scene is determined,and the task modeling of the event scene is conducted.Next,the standard operating procedures are decomposed into different entities,identifying key and important operational entities and paths.The parameters for processing time and processing capacity of the functional servers representing various brain regions in the model are determined,and error probabilities for the key and important operational entities are assigned using human reliability methods,leading to 24 simulation runs to obtain results.Finally,through the design of a simulated flight experiment,the results of the selected indexes of the experiment were analyzed,and the experimental results and simulation results were compared to verify the feasibility of the QN MHP model in the study of human-computer interaction in the cockpit of civil aircraft.The findings indicate that in the airspeed unreliable handling tasks for the Airbus A320,pilots are prone to human errors along the handling path,with a few errors at critical nodes such as fault identification and judgment.The eye utilization of pilots is relatively high during the task process.It is concluded that the QN MHP model is suitable for the study of human-computer interaction in the cockpit of civil aircraft,and the excessive eye load of pilots is one of the reasons for the failure of human-computer interaction in the cockpit,which should be paid more attention in the design of human-computer interaction process and flight training in the future.

关 键 词：安全人体学 驾驶舱人机交互 认知建模 人的排队网络信息加工模型 空速不可靠 

分 类 号：X949[环境科学与工程—安全科学]