摘要
驾驶操作疲劳是引起交通事故、造成驾驶员职业病的主要原因之一。由于疲劳本身的不确定性,导致驾驶操作疲劳评价测试工作一直存在较大的困难。基于现有驾驶操作疲劳评价测试方法的研究现状对未来趋势进行分析和展望。通过检索关键词,阅读整理相关文献,了解目前交通运输工具和工程车辆所使用的驾驶操作疲劳评价测试方法,分为主观判断疲劳评价测试(如问卷调查、自评量表等)和客观判断疲劳评价测试(如脑电图(EEG)、面部识别等)。研究表明,了解受试者真实的生理和精神状态,是有效避免交通事故发生和预防驾驶员职业病的重要途径。最后,得出未来的研究趋势将是努力提高生理特征测量的稳定性、面部识别的准确率、数据获取的真实性以及构建统一的驾驶操作疲劳评估模型。
Driving fatigue is one of the main causes of traffic accidents and occupational diseases.Owing to the uncertainty of fatigue itself,there are always great difficulties in the fatigue test of driving operation.On the basis of the current research status of driving fatigue evaluation and test methods,the future trend was analyzed and prospected.By searching keywords and reading and sorting relevant literature,the current driving fatigue evaluation test methods used in transportation vehicles and engineering vehicles were classified as subjective judgment fatigue evaluation test,such as questionnaire survey and self-rating scale,and objective judgment fatigue evaluation test,such as electroencephalogram(EEG)and facial recognition.The research shows that it is an important way to avoid traffic accidents and prevent drivers from occupational diseases to understand the subjects'real physical and mental state.Finally,it is concluded that the future research trend will be focused on improving the stability of physiological feature measurement,the accuracy of facial recognition,the authenticity of data acquisition,and the construction of a unified driving fatigue assessment model.
作者
范沁红
江星辰
杨刚俊
田保珍
武学良
聂敏
FAN Qinhong;JIANG Xingchen;YANG Gangjun;TIAN Baozhen;WU Xueliang;NIE Min(School of Mechanical Engineering, Taiyuan University of Science and Technology, Taiyuan 030024, China;CRRC Datong CO., LTD., Datong 037038, China)
出处
《太原理工大学学报》
CAS
北大核心
2021年第4期645-653,共9页
Journal of Taiyuan University of Technology
基金
山西省科技平台资助项目(201805D121006)
山西省科技重大专项资助项目(20181102002)
太原科技大学博士启动项目(20182034)
山西省重点研发计划项目(201803D31075)。
关键词
驾驶疲劳
疲劳测试
生理特征测量
面部识别
driving fatigue
fatigue test
measurement of physiological characteristics
facial recognition