疲劳是导致民机复合材料结构目视检查差错的重要诱因，疲劳检测对于减少人的差错，保障飞行安全具有重要意义。对基于眼动行为的疲劳度量与检测方法进行了研究，建立了民机复合材料结构目视检查实验场景，利用Tobii眼动仪提取了正常状态和疲劳状态下的目视检查眼动数据，分析了瞳孔直径、平均注视时间、平均注视频率、平均眼跳时间、平均眼跳频率、注视热点与轨迹和扫视速度等眼动行为与疲劳的关系，进而提取了能表征疲劳的瞳孔直径、平均注视时间和扫视速度3种眼动指标，以该指标构建特征向量，利用支持向量机（SVM）方法构建了目视检查疲劳检测模型。研究发现疲劳状态下的目视检查平均注视时间更长，扫视速度更慢、瞳孔直径减小，右瞳孔减小程度更大，核函数为径向基函数和高斯函数的SVM方法对疲劳的检测效果好。研究结果表明，利用SVM方法训练由瞳孔直径、平均注视时间和扫视速度构成的眼动特征向量能有效检测目视检查中的疲劳状态。
Fatigue is an important cause of human error in visual inspection of civil aircraft composite material components. The measurement of fatigue has great implications on reduction of human error and flight safety. To measure and detect fatigue, an eye movement behavior based method is proposed. The experimental scene of composite material visual inspection is established. Tobii eye tracking is used to extract the eye movement data in the experiment under normal working condition and fatigue condition. The relationships between fatigue and means of pupil diameter, fixation time, fixation frequency, saccadic time, saccadic frequency, fixation heat map and saccadic velocity were analyzed. Then, three kinds of eye movement indexes, namely, pupil diameter, saccadic velocity and average fixation time, which could represent fatigue, are extracted to construct feature vectors for Support Vector Machine (SVM) method to build the fatigue detection model. It is found that the average fixation time is longer, and the saccadic velocity and the pupil diameter are smaller under fatigue in visual inspection, especially the pupil of the right eye. The SVM method with kernel function as radial basis function and gaussian function has a good effect on fatigue detection. The experimental results show that the SVM method using the eye movement feature vector can effectively detect the fatigue state in visual inspection.
[1] BAARAN J. Visual inspection of composite structures[R]. Braunschweig:Institute of Composite Structures and Adaptive Systems, 2009.
[2] OSTERJR C V, STRONG J S, ZORN C K. Analyzing aviation safety:Problems, challenges, opportunities[J]. Research in Transportation Economics, 2013, 43(1):148-164.
[3] LATORELLA K A, PRABHU P V. A review of human error in aviation maintenance and inspection[J]. International Journal of Industrial Ergonomics, 2000, 26(2):133-161.
[4] KHAROUFAH H, MURRAY J, BAXTER G, et al. A review of human factors causations in commercial air transport accidents and incidents:From to 2000-2016[J]. Progress in Aerospace Sciences, 2018, 99(5):1-13.
[5] LEE S, KIM J K. Factors contributing to the risk of airline pilot fatigue[J]. Journal of Air Transport Management, 2018, 67(3):197-207.
[6] LOBO J L, SER D, MORAVEK Z, et al. Cognitive workload classification using eye-tracking and EEG data[C]//International Conference on Human-computer Interaction in Aerospace. New York:ACM, 2016:1-8.
[7] NEALLEY M A, GAWRON V J. The effect of fatigue on air traffic controllers[J]. The International Journal of Aviation Psychology, 2015, 25(1):14-47.
[8] 卜建, 刘银鑫, 王艳军. 空中交通管制员的眼动行为与疲劳关系[J]. 航空学报, 2017, 38(S1):52-57. BU J, LIU Y X, WANG Y J. Relationship between air traffic controllers' eye movement and fatigue[J]. Acta Aeronautica et Astronautica Sinica, 2017, 38(S1):52-57(in Chinese).
[9] WANG T C, CHUANG L H. Psychological and physiological fatigue variation and fatigue factors in aircraft line maintenance crews[J]. International Journal of Industrial Ergonomics, 2014, 44(1):107-113.
[10] 冯贺. 民航机务维修人员疲劳管理研究[D]. 天津:中国民航大学, 2016. FENG H. Research on fatigue management of aircraft maintenance personnel[D]. Tianjin:Civil Aviation University of China, 2016(in Chinese).
[11] DAI J, LUO M, HU W, et al. Developing a fatigue questionnaire for Chinese civil aviation pilots[J]. International Journal of Occupational Safety and Ergonomics, 2020, 26(1):37-45.
[12] 李长勇, 吴金强, 房爱青. 基于多信息的疲劳状态识别方法[J]. 激光与光电子学进展, 2018, 55(10):239-245. LI C Y, WU J Q, FANG A Q. A multi-information based fatigue state recognition method[J]. Laser & Optoelectronics Progress, 2018, 55(10):239-245(in Chinese).
[13] 牛清宁, 周志强, 金立生, 等.基于眼动特征的疲劳驾驶检测方法[J]. 哈尔滨工程大学学报, 2015, 36(3):394-398. NIU Q N, ZHOU Z Q, JIN L S, et al. Detection of driver fatigue based on eye movements[J].Journal of Harbin Engineering University,2015, 36(3):394-398(in Chinese).
[14] LENSKIY A A, LEE J S. Driver's eye blinking detection using novel color and texture segmentation algorithms[J]. International Journal of Control Automation and Systems, 2012, 10(2):317-327.
[15] MANDAL B, LI L, WANG G S, et al. Towards detection of bus driver fatigue based on robust visual analysis of eye state[J]. IEEE Transactions on Intelligent Transportation Systems, 2016, 18(3):545-557.
[16] YAMADA Y, KOBAYASHI M. Fatigue detection model for older adults using eye-tracking data gathered while watching video:Evaluation against diverse fatiguing tasks[C]//International Conference on Healthcare Informatics. Piscataway:IEEE Press, 2017:275-284.
[17] 靳慧斌,朱国蕾,吕川. 基于支持向量机的管制疲劳检测模型研究[J]. 安全与环境学报, 2019, 19(1):105-111. JIN H B, ZHU G L, LU C. On the air traffic controller's fatigue detection based on the support vector machine[J]. Journal of Safety and Environment, 2019, 19(1):105-111(in Chinese).
[18] 刘亚威. 管制疲劳的眼动指标研究[D]. 天津:中国民航大学, 2018. LIU Y W. The research of eye movement index for detecting air traffic controllers' fatigue[D]. Tianjin:Civil Aviation University of China, 2018(in Chinese).
[19] STASIL L D, MCCAMY M B, SUSANA M C, et al. Effects of long and short simulated flights on the saccadic eye movement velocity of aviators[J]. Physiology & Behavior, 2016, 153(1):91-96.
[20] 汪磊, 任勇. 机务维修人员疲劳风险评价模型及管理系统实现[J]. 中国安全科学学报, 2017, 27(5):70-75. WANG L, REN Y. Fatigue risk evaluation model and system for civil aviation maintenance personnel[J]. China Safety Science Journal, 2017, 27(5):70-75(in Chinese).
[21] 李天任. 机务人员疲劳的特征研究[D]. 天津:中国民航大学, 2017. LI T R. Study on the characteristics of fatigue of aviation maintenance[D]. Tianjin:Civil Aviation University of China, 2017(in Chinese).
[22] VAPNIK V N. Statistical learning theory[M]. New York:Wiley-Interscience, 1998.
CJA