基于驾驶操作行为的驾驶员疲劳状态识别模型研究

以驾驶疲劳状态监测为研究对象,介绍现有几种疲劳检测方法及其优缺点,提出把驾驶行为操作和驾驶员生理指标相结合建立疲劳识别模型的思想。通过大量模拟器驾驶实验,建立驾驶操作和驾驶员生理指标之间的关系模型,并运用最小二乘法对数学模型进行了参数识别。利用驾驶员生理指标能较好判别驾驶员状态特性的特点,找出驾驶操作行为和驾驶状态之间的关系。研究结果有助于建立驾驶操作行为和驾驶员疲劳状态之间的关系模型。     

基于DSP虹膜识别防疲劳驾驶报警系统的研究

防止疲劳驾驶以主观监测和客观检测为主,但其在可靠性、成本、检测方法上存在不足,为此,设计了一套基于DSP虹膜识别防止疲劳驾驶报警系统。借鉴国内外学者的研究,遵循实时性、准确性、简洁性及经济性的设计原则,以虹膜识别算法为依据,DSP微处理器控制技术为基础进行了开发,该报警系统可在不干扰驾驶员的情况下,识别驾驶员身份,记录驾驶时间,识别疲劳驾驶并报警。测试结果表明:系统结构简单,实现了模块化。虹膜识别模块、计时模块基本满足了准确性和实时性的要求。     

车载驾驶员疲劳驾驶预警与控制系统研究

为了识别与安全控制疲劳危险驾驶行为,有效预防与减少因疲劳危险驾驶导致的交通事故,基于疲劳检测分级、预警与自动智能控制技术,开发出车载驾驶员疲劳驾驶实时监测预警与控制系统。首先基于PERCLO方法,构建驾驶员疲劳检测与分级模型;然后根据所输出的驾驶员疲劳等级信息,提出疲劳驾驶三级预警原理,及其预警实现方式;最后以疲劳预警信息为基础,形成基于驾驶员不同疲劳等级预警的安全控制技术,并对处于深度疲劳的危险驾驶行为,构建自动智能紧急控制停车系统,重点阐述系统的地形匹配、智能控制,以及自动驾驶与停车三大核心技术,并提出相应的系统硬件构成,为系统工程应用提供理论与技术支持。     

闪光融合频率测试法在北京公交驾驶员中的应用

通过对北京公交驾驶员的心理疲劳研究,探索三种车型司机在驾驶不同圈数时的大脑觉醒程度变化规律,防止驾驶员因疲劳驾驶而造成的交通事故。利用闪光融合频率值测试法,对三条典型线路的驾驶员进行测试,并利用Wilcoxon非参数检验方法,使用SPSS软件检验数据变化的显著性。驾驶铰链式加长客车的驾驶员和驾驶单机客车的驾驶员闪光融合频率值在工作两圈时发生显著降低P<0.05,驾驶双层客车的驾驶员闪光融合频率值变化不显著P>0.05。     

道路交通环境中驾驶疲劳的生成模型研究

为预防由驾驶疲劳引起的交通事故,有必要研究在道路、交通和环境的综合影响下驾驶疲劳的生成机理。基于生理、心理学中的经典理论,借鉴国内外相关的研究成果,采用理论推理的方法对驾驶疲劳生成过程中驾驶员唤醒水平的变化规律及其影响因素进行分析。在此基础上建立了驾驶疲劳的生成模型,并将模型应用于工程实际。通过驾驶员唤醒水平的变化,指出驾驶疲劳的生成时刻,及其对驾驶时间的规定和道路、景观设计的影响。该模型以唤醒水平为核心,描述驾驶疲劳生成过程中驾驶员唤醒水平的变化规律,强调道路交通环境对驾驶员唤醒水平的影响。     

真实条件下长时间作业的驾驶安全性影响研究

为研究长时间单调驾驶对驾驶员疲劳、嗜睡、反应时间和驾驶速度的确切影响,以合作企业3系重卡为操作对象进行了一组真实驾驶条件试验。在自愿的基础上随机地从合作企业物流公司选择12名经验丰富的驾驶员作为试验的驾驶员样本。试验采用主观评分方法记录试验者的嗜睡和疲劳状况,所有数据分析基于统计学软件PASW Statistic 18.0。试验结果表明长时间单调驾驶会导致驾驶员疲劳和嗜睡,而疲劳和嗜睡在一定的程度上会导致驾驶速度的加快,却没有导致驾驶员反应时间的显著变化。在持续驾驶3 h之后驾驶员的疲劳和驾驶绩效发生了明显劣化,故从安全的角度考虑应以2~3 h为界合理安排司机的作业负荷和绩效考评。     

基于EEG频谱特征的驾驶员疲劳监测研究

研究表明疲劳驾驶是引发交通伤亡事故的重要原因之一,因此有必要采取相应的预防措施。脑电是公认的睡眠(疲劳)金指标,因此论文提出了基于脑电频谱特征的驾驶员疲劳预测方法。采用了驾驶模拟实验中记录的三路驾驶员脑电信号,并利用驾驶员自评与专家评定两种方式相结合的方法将驾驶数据分为疲劳和清醒。针对脑电中眼电噪声很强的特点,对记录的脑电进行了自适应滤波消噪处理,结果显示可有效滤除眼电伪迹;然后根据脑电的频域特征比较突出且与疲劳相关的特点,从去噪后的脑电中提取出了的75个频谱特征;最后利用这些频谱特征,采用朴素贝叶斯分类的方法建立了驾驶员疲劳监测模型。实验结果表明,该方法能监测出驾驶员84%的疲劳状态。     

地铁驾驶员驾驶疲劳状态监测

为监测地铁自动驾驶系统驾驶模式下驾驶员驾驶疲劳状态,以S地铁公司的驾驶员为研究对象,开展驾驶员疲劳主、客观监测研究。主观监测应用《自觉症状调查表》调查并统计分析地铁驾驶员的驾驶主观疲劳感受;客观监测应用Eegosports 64通道无线脑电肌电系统测量地铁驾驶员在各班次、各时间段的脑电(EEG)信号,并结合Matlab工具箱中的EEGLAB分析各班次驾驶员EEG中δ波的频谱图。结果表明:驾驶员驾驶疲劳总体的平均得分为1.8分,即驾驶疲劳有些明显,且晚班和夜班驾驶疲劳比白班的大,从主客观2方面说明驾驶员处于疲劳驾驶状态。     

生理疲劳和心理疲劳对车辆驾驶的影响对比

针对现有疲劳驾驶预警和干预技术研究鲜有对生理疲劳和心理疲劳进行区分考虑的问题,为对比这两类典型疲劳态对驾驶员车辆驾驶过程的事故倾向影响,分别从性别、年龄和驾龄的角度分3批次共招募90位驾驶员进行状态诱发和驾驶实验。结果表明:尽管生理疲劳和心理疲劳都会如传统研究所述导致各驾驶员的驾驶违规倾向增加和驾驶能力降低,但是二者对于各类别驾驶员的驾驶影响程度和规律存在差异甚至迥异。研究疲劳驾驶相关问题时有必要首先判断驾驶员是生理疲劳还是心理疲劳,这是一个被普遍忽视而又可能影响研究结论准确性和有效性的重要因素。     

生理疲劳和心理疲劳对车辆驾驶的影响对比北大核心CSCD

针对现有疲劳驾驶预警和干预技术研究鲜有对生理疲劳和心理疲劳进行区分考虑的问题,为对比这两类典型疲劳态对驾驶员车辆驾驶过程的事故倾向影响,分别从性别、年龄和驾龄的角度分3批次共招募90位驾驶员进行状态诱发和驾驶实验。结果表明:尽管生理疲劳和心理疲劳都会如传统研究所述导致各驾驶员的驾驶违规倾向增加和驾驶能力降低,但是二者对于各类别驾驶员的驾驶影响程度和规律存在差异甚至迥异。研究疲劳驾驶相关问题时有必要首先判断驾驶员是生理疲劳还是心理疲劳,这是一个被普遍忽视而又可能影响研究结论准确性和有效性的重要因素。     

基于驾驶员模型参数辨识的疲劳驾驶研究

提出一种利用驾驶员模型反演方法来进行驾驶员疲劳诊断研究的新方法。首先利用预瞄神经网络建立适应于复杂路况条件下的驾驶员-汽车-道路闭环模型,然后定义特定行驶轨迹内理论数据与试验数据的近似度为目标函数,将驾驶员参数的反演问题转化为多目标优化问题,采用基于实数编码混沌变异量子遗传算法的优化方法,获得全局最优解。试验中采用脑电和主观疲劳心理评测结合的方法确定被试者的疲劳状况。在每种疲劳状况下对驾驶员参数进行辨识,对结果进行统计分析表明,在考虑到车型、道路曲率等因素条件下驾驶员参数分布与驾驶员的疲劳状况有很强的相关性。     

基于G_1法的飞行疲劳综合评价指标体系研究

为综合控制并评价飞行疲劳风险,通过对疲劳影响因素的深入分析,运用层次分析法(AHP)确定疲劳风险评价指标,依据G1法编制专家调查问卷,采用专家独立调查方法对指标进行判断,根据G1法确定各指标权重,建立飞行疲劳综合评价指标体系,实现对疲劳风险的量化综合评价。结果表明:运用G1法能有效地综合利用影响疲劳的各种信息评价飞行员的疲劳状况,该指标体系与现有控制飞行疲劳风险的影响因素吻合较好,可以作为进一步实现疲劳风险量化的基础。     

Issues with using police citations to assign responsibility in quasi-induced exposure

Crash fault determination is one of the most critical issues in applications of quasi-induced exposure. Traditionally, the driver citation issued by the investigating police officer is the primary source to assign responsibility for motor vehicle crashes. Such citations are based on the “evidence” or observation of a moving violation (such as engaged hazardous actions) in combination with non-moving violations (such as suspended driver license) prior to the crash. The objective here is to identify the contributing factors that may lead to driver citations in two-vehicle crashes in addition to the hazardous action. Multivariate binary logistic regression modeling is employed to explore the behavior of the investigating police officer in terms of issuing citation at the crash scene. A series of explanatory parameters including roadway characteristics, environmental factors, and driver and vehicle attributes is assessed. The results show that whether the crash type was a hit-and-run, alcohol and illegal drug use, driver gender, driver age, and injury severity all appear to have significant impacts on the investigating officer’s decision-making. Specific examples are given to demonstrate how two factors hit-and-run and drinking status can skew the exposure estimates in the context of quasi-induced exposure. The findings will help to serve as a basis to select appropriate parameters in assigning crash responsibility in quasi-induced exposure applications; and we make recommendations to modify existing crash database for better safety research in the future.     

Structural reliability analysis of contact fatigue design of gears in wind turbine drivetrains

Advances in the design of large scale wind turbines have raised an interest for more optimized life cycle design of mechanical components (e.g. gears, bearings, shafts, etc.), with a better understanding of their performance over time. Development of the non-systematic, often deterministic design methods followed by the application of corresponding design standards that incorporate experience from current common practice have managed to produce mechanical components that comply with minimum safety requirements. However, such approaches cannot achieve optimized mechanical components, neither account for the performance over their service lives. Reliability-based design currently represents the most advanced method in order to achieve the targets mentioned above, by explicitly considering uncertainty of design variables. This paper describes a structural reliability method (SRM) for fatigue analysis of mechanical components of wind turbines. The method is based on the ‘so-called’ limit state functions of relevant failure modes. Two gear tooth fatigue failure modes (surface and subsurface pitting) were considered. The method is exemplified by a time-domain based gear contact fatigue analysis of the National Renewable Energy Laboratory's 750 kW land-based wind turbine. The sensitivity of the reliability index on some random parameters used for reliability-based gear contact fatigue analysis is estimated. The effect of inspection on reliability analysis is also briefly investigated.     

Fatal crash trends for Australian young drivers 1997-2007: Geographic and socioeconomic differentials

Background

Little has been published on changes in young driver fatality rates over time. This paper examines differences in Australian young driver fatality rates over the last decade, examining important risk factors including place of residence and socioeconomic status (SES).

Methods

Young driver (17-25 years) police-recorded passenger vehicle crashes were extracted from New South Wales State records from 1997-2007. Rurality of residence and SES were classified into three levels based on drivers’ residential postcode: urban, regional, or rural; and high, moderate, or low SES areas. Geographic and SES disparities in trends of fatality rates were examined by the generalized linear model. Chi-square trend test was used to examine the distributions of posted speed limits, drinking driving, fatigue, seatbelt use, vehicle age, night-time driving, and the time from crash to death across rurality and socioeconomic status.

Results

Young driver fatality rate significantly decreased 5% per year (p < 0.05); however, stratified analyses (by rurality and by SES) showed that only the reduction among urban drivers was significant (average 5% decrease per year, p < 0.01). The higher relative risk of fatality for rural versus urban drivers, and for drivers of low versus high SES remained unchanged over the last decade. High posted speed limits, fatigue, drink driving and seatbelt non-use were significantly associated with rural fatalities, whereas high posted speed limit, fatigue, and driving an older vehicle were significantly related to low SES fatality.

Conclusion

The constant geographic and SES disparities in young driver fatality rates highlight safety inequities for those living in rural areas and those of low SES. Better targeted interventions are needed, including attention to behavioral risk factors and vehicle age.     

Behavioral Factors as Predictors of Motor Vehicle Crashes in Young Drivers

Gains in reducing mortality and morbidity from motor vehicle crashes can be achieved by understanding the behavioral factors that contribute to the elevated risk of motor vehicle-related injury and death. This study investigates the incidence, along with the effect of driver and behavioral factors, on the likelihood of motor vehicle crashes. Seventeen year old newly licensed drivers (n = 1277) in Perth, Western Australia, were recruited and followed over the first 12 months of driving. Using Cox proportional hazard analysis, driver and behavioral factors were assessed to determine whether they predicted the likelihood of a crash in the first 12 months of driving. The crash incidence rate was higher for males (1R = 4.6/10,000 driving days) than females (IR = 3.9/10,000 driving days). Multivariate analysis indicated that drivers who reported to have driven daily prior to obtaining their learners permit (L-plates) were at an increased risk of motor vehicle crash. A twofold increase in motor vehicle crash was apparent among drivers considered to be confident-adventurous drivers compared to low to moderate levels of driver confidence-adventurousness (HR = 2.04, 95% CI = 1.29-3.21). The research indicates that a driver's perception of their confidence and adventurousness in the road environment plays a part in the causal pathway leading to a motor vehicle crash. This research points to the need for preventive strategies that focus not only on knowledge and skill acquisition, but also the driver's perception in preparing young people for our roads.     

桥梁实用延性抗震设计方法研究

针对铁路桥梁中应用广泛的单柱式桥墩 ,考虑多种跨度 ,多种墩高和多种场地及多种地震烈度的情况 ,在进行大量的桥墩结构线性和非线性弹塑性动力计算分析的基础上 ,通过对大量数据的统计分析 ,得到桥墩线弹性最大弯矩比和非线性位移延性比参数的变化规律 ,基于概率性的结构随机地震反应理论 ,建立了由线弹性动力分析结果来估算桥墩结构的位移延性响应的方法。