基于视频分析的空管员违规行为识别方法*

为利用视频数据对空管员违规行为进行智能化分析,降低不安全事件发生率,提出2阶段的违规行为识别模型（AR-ResNeXt）,基于实地调研构建空管员视频数据集,利用最小化动态多实例学习损失函数和中心损失函数,获得违规行为检测的判别特征表示,结合异常回归网络和ResNeXt网络,完成对空管员违规行为的时序区间检测与动作分类。研究结果表明:AR-ResNeXt模型在自制数据集中,其帧级AUC达到82.9%,分类准确率达到87.8%,可准确识别空管员发生违规行为的时序区间并进行分类,研究结果可为保障空中交通安全奠定基础。     

民航空管安全文化建设探析

根据民航空管安全发展的客观规律,在综合考虑践行空管持续安全理念、减少空管人为差错、建设空管安全管理体系的基础上,提出要实现我国民航的持续安全,就要构建并不断完善空管安全文化建设的有效手段和途径。对空管安全文化建设的途径展开了深入探索,并提出了相关建议和措施,包括开展技能竞赛等文化娱乐活动、建立管制员心理培训与辅导机制、提升管制员新技术适应能力等。空管安全文化的建设是空管发展的坚强后盾,有效手段和措施建设的推进将成为航空运行安全的有力保障。     

空中交通管制员与飞行员通信风险评估指标体系研究

对空管安全风险管理的关键环节——管制员与飞行员的通信过程进行分析,探讨管制员与飞行员通信失误的表现,分析造成通信失误的原因,从人员、设备、环境和管理4个方面探讨通信风险因素。在此基础上,构建管制员与飞行员通信风险评估指标体系,包括总体层、因素层和指标层3个层次及18项评估指标。通过对通信风险进行监测、评价和管控,帮助管理人员发现通信过程存在的安全隐患,增强管制员与飞行员通信工作的可靠性,从而提高空中交通安全水平。     

Estimation of air traffic longitudinal conflict probability based on the reaction time of controllers

To estimate air traffic longitudinal conflict probability influenced by human factors, an analytic model considering the reaction time of controllers is proposed. In the model, the decelerating process of two close flights is described, and the reaction time of controllers is considered a stochastic variable. Then one hundred data of the controller reaction time are collected and analysed. Maximum likelihood estimate is used for parameter estimation. The Anderson–Darling Goodness of Fit test is used for significance test. The results show that the reaction time of controllers fits lognormal distribution at levels of significance 0.05, 0.025, 0.01 and 0.005 respectively. Case study is then performed to certify the rationality of the model, and the impact of the controller reaction time on air traffic longitudinal conflict probability is shown.     

管制员认知偏差测评量表的编制与应用

利用信息加工模型,结合管制工作的特殊性,编制出管制员认知偏差测评量表。利用该量表对管制员认知偏差进行测量,结果表明管制员管制过程中存在较大的认知偏差;不同性别及年龄的管制员在认知偏差方面存在显著差异。     

基于信息加工模型的管制员差错分类与分析

在Wickens的人类信息加工模型的基础上,加入注意功能、情景意识、内部和外部操作成形因素,建立了管制员信息处理模型。按照该模型,空中交通管制人为差错可按照认知领域分为感知与警觉性差错、短时记忆差错、长时记忆差错、判断与计划差错、响应选择差错和响应执行差错;影响管制员操作的情境条件可分为外部操作成形因素和内部操作成形因素。对以往空管人为差错的分析表明,在信息加工层面分类的人为差错更宜于确定差错的心理致因。基于该理论模型的差错分类系统可以改进人为差错分析的有效性和一致性,从而提高差错管理的有效性。     

空中交通管制员职业素质模糊综合评价

提出一种管制员综合素质的评价方法;构建管制员综合素质评价指标体系和模糊综合评价模型;应用专家打分法确定指标的权重判断矩阵数据和隶属度数据;采用层次分析法对判断矩阵进行处理得到指标权重数据;按照评价模型的程序对权重数据和隶属度数据进行处理,最终得到管制员综合素质的评价值,根据评价结果提出了提高管制员综合素质的对策。     

Errors of perception in air traffic control

Accurate and timely perception of visual and auditory information by air traffic controllers is critical to aviation safety. The aim of this research was to investigate the types of errors of perception that occur in air traffic control (ATC). The data were gathered from interviews with 28 UK area controllers and a review of 48 area and terminal control incidents involving loss of separation in the UK spanning three years. The data gave rise to a set of classifications, which form part of the technique for the retrospective analysis of human error (TRACEr). The results are discussed in terms of theory and empirical research. Key main implications for future automation are outlined, in terms of display design, automation reliability and the operation of multiple tools designed and developed separately.     

Working and Health Conditions of Italian Air Traffic Controllers

The paper summarises some studies carried out in recent years on Italian air traffic controllers. Work stress appeared related mainly to mental charge, aggravated by time pressure and high responsibility. Shiftwork was not considered highly stressful, thanks to the good shift schedules adopted. The disorders most frequently complained of had a prevalent psychosomatic component, concerning the digestive, neuropsychic, and cardiovascular systems. However, their prevalence was lower than, or similar to, that recorded in general population. The controllers engaged in regional centres showed slightly worse health conditions than those engaged in airport towers; the same was found in the radar controllers compared to those working in non-radar positions.     

管制员安全能力模型研究

为准确评价管制员安全能力,基于能力的定义和管制员工作职责,界定管制员安全能力的内涵;依据该内涵及其工作特性,建立由身体素质、业务素质和意识3个结构维度组成的管制员安全能力模型。其中,身体素质包括生理状况和心理状况;业务素质包括教育状况、培训状况、技能状况和经验状况;意识包括安全意识和工作意识。在各项指标性质差异较大情况下,利用功效系数法实现评价指标的标准化以减小误差,客观反映指标情况,同时采用G1-法和熵值法集成的主客观综合赋权法确定指标的权重,在一定程度上弥补主客观单一赋权的不足,最后通过逼近理想解排序法(TOPSIS)评价管制员安全能力。结果表明,按照从大到小排序对管制员安全能力的影响因素依次为意识、身体素质和业务素质。就对所论能力的影响而言,心理状况强于生理状况;技能状况强教育、培训和经验状况;安全意识对意识的影响大于工作意识。     

Coding ATC incident data using HFACS: Inter-coder consensus

Reliability studies for coding contributing factors of incident reports in high hazard industries are rarely conducted and reported. Although the Human Factors Analysis and Classification System (HFACS) appears to have a larger number of such studies completed than most other systems doubt exists as the accuracy and comparability of results between studies due to aspects of methodology and reporting. This paper reports on a trial conducted on HFACS to determine its reliability in the context of military air traffic control (ATC). Two groups participated in the trial: one group comprised of specialists in the field of human factors and the other group comprised air traffic controllers. All participants were given standardised training via a self-paced workbook and then read 14 incident reports and coded the associated findings. The results show similarly low consensus for both groups of participants. Several reasons for the results are proposed associated with the HFACS model, the context within which incident reporting occurs in real organisations and the conduct of the studies.     

A mobile flight case learning system for ATC miscommunications

Aviation’s highest priority is safety. The primary risk to safety derives not from automated systems but from human factors, most notably air traffic control. We present results from development of a flight case learning system designed to operate on mobile phones used by air traffic controllers (ATCs). Our system takes advantage of key Ontology concepts, a case-based system development procedure, human-centered design (HCD) strategies, and appropriate small-screen interface design protocols. A questionnaire to assess user interaction satisfaction (QUIS) was deployed for subsequent usability testing and to verify acceptance of, and satisfaction with, the system. Twelve subjects participated in the questionnaire-based evaluation of subjective satisfaction. In addition, two flight experts served on a review panel for domain knowledge verification and acceptance of the interface design. Our results confirm that the system is a suitably designed mobile learning system that can accelerate self-learning for ATCs.     

Work domain analysis for air traffic controller weather displays

INTRODUCTION: Adverse weather conditions have a major impact on National Airspace System (NAS) operations. They create safety hazards for pilots, constrain the usable airspace for air traffic control (ATC), and reduce the overall capacity of the NAS. A system-wide dissemination of weather information to controllers could theoretically improve safety and efficiency. PROBLEM: However, it is currently unclear what weather information would be beneficial for tactical operations. Furthermore, no previous research has empirically evaluated optimal presentation designs for ATC weather displays. Ill-designed weather displays can cause safety hazards by presenting redundant information (i.e., by increasing the cognitive load) and display clutter (e.g., by interfering with the visual extraction of traffic data). METHOD: In the present paper, we outline our use of cognitive work analysis (CWA) techniques for the assessment of weather information needs for terminal controllers. RESULTS: Specifically, we describe how the CWA modeling tools helped us reveal instances in the terminal domain where weather information is lacking or insufficiently disseminated. We used our CWA results to drive the development of weather display concepts and to set up a high-fidelity simulation capability. IMPACT ON INDUSTRY: By means of high-fidelity simulations, we can empirically evaluate controller weather information needs in order to propose weather displays for increased aircraft safety and efficiency of terminal operations.     

基于粗神经网络的管制员工作差错风险预警模型

针对空中交通管制员工作差错风险类型,指出指标体系建构过程的动态性特征,从个人、团队、设备、环境及管理几个方面,建构预警指标体系,运用粗糙集在数据挖掘方面的优势,通过基于属性重要度的启发式约简算法,提取关键指标,剔除冗余指标,可以实现在不丢失关键预警监控对象的情况下,结合BP人工神经网络构建实时预警模型,既有利于加快运算速度,又有利于进行重点监控.经过实例仿真,粗糙集与BP网络结合建构的预警模型,能有效针对管制员工作差错风险进行实时预警监控.     

Quantifying the impact of adaptive traffic control systems on crash frequency and severity: Evidence from Oakland County,Michigan

IntroductionDespite seeing widespread usage worldwide, adaptive traffic control systems have experienced relatively little use in the United States. Of the systems used, the Sydney Coordinated Adaptive Traffic System (SCATS) is the most popular in America. Safety benefits of these systems are not as well understood nor as commonly documented.MethodThis study investigates the safety benefits of adaptive traffic control systems by using the large SCATS-based system in Oakland County, MI known as FAST-TRAC. This study uses data from FAST-TRAC-controlled intersections in Oakland County and compares a wide variety of geometric, traffic, and crash characteristics to similar intersections in metropolitan areas elsewhere in Michigan. Data from 498 signalized intersections are used to conduct a cross-sectional analysis. Negative binomial models are used to estimate models for three dependent crash variables. Multinomial logit models are used to estimate an injury severity model. A variable tracking the presence of FAST-TRAC controllers at intersections is used in all models to determine if a SCATS-based system has an impact on crash occurrences or crash severity.ResultsEstimates show that the presence of SCATS-based controllers at intersections is likely to reduce angle crashes by up to 19.3%. Severity results show a statistically significant increase in non-serious injuries, but not a significant reduction in incapacitating injuries or fatal accidents.     

管制员不安全行为干预策略研究

为了制定科学合理的干预策略、防止由管制员导致的两机相撞等不安全事件发生,运用系统动力学方法(SD)构建了管制员不安全行为干预策略模型,以S空管站为例,运用Vensim软件仿真模拟不同安全奖惩政策对管制员不安全行为的干预结果。结果表明:安全奖励政策可以有效干预管制员的差错行为,安全惩罚政策可以有效干预管制员的违章行为;高强度奖励政策-中强度惩罚政策组合干预效果最佳,即当对管制员奖励强度达管制员月薪的3.2倍,惩罚强度达管制员月薪的0.82倍,管制员不安全行为造成的不安全事件率能够降低85.6%。     

基于CREAM和贝叶斯网络的空管人误概率预测方法

针对研究管制人因可靠性时存在的模糊性和片面性问题,采用认知可靠性与失误分析方法（CREAM）中的扩展预测法,计算10项管制通用任务的人误概率;在此基础上,以管制行为形成因子作为根节点构建贝叶斯网络,建立其与情景控制模式的不确定关系模型,对管制员在多任务中的人误概率进行预测。研究结果表明:在由相同评判者给出行为形成因子影响效应的前提下,由CREAM扩展预测法和构建贝叶斯网络的方法预测得到的多数任务的人误概率差异较大,从方法的客观性、合理性和适用性角度分析,贝叶斯网络在研究该问题时更具优势。     

管制员人为差错影响因素及指标权重分析

根据SHELL模型,将影响管制员人为差错的因素从内部因素和外部因素进行分析,内部因素包括管制员生理因素、心理因素、管制员业务技能三个部分;外部因素包括管制员与管制员班组之间、管制员与管制设备之间、管制员与管制程序等软件之间。通过分析和专家咨询,建立了影响管制员人为差错的影响因素指标体系,在模糊层次分析法的基础之上引入0.1-0.9标度法的三角模糊数,通过对各影响因素进行对比分析,得出了影响管制员人为差错的三级指标的重要度排序,排在前八位的因素依次为酒精及药物影响、形势意识、班组人员性格搭配、班组人员能力搭配、疲劳、人机界面、外界压力、情绪状态。为管制员培训和管理层进行安全检查提供了基础理论依据。     

A model of the air traffic controller's picture

This paper reviews the development of a model of the air traffic controller's mental image, ‘picture’, or situation awareness, used for controlling air traffic. The computerised model's development, origins and theoretical basis are outlined, and the model is described in some detail in the context of current air traffic operations. The model can be utilised to explore the potential impacts of future automation on the cognitive performance of the air traffic controller. The general potential contributions of the area of cognitive modelling to system design and training in accelerating industries such as air traffic control, are also discussed.     

基于Fuzzy-ANP的空管安全风险评估研究

空中交通管制对于保障飞行安全至关重要,如何进行空管安全风险评估是亟待研究的问题。在分析三角模糊数学和ANP原理的基础上,针对空管安全风险因素相互影响的特点,建立基于Fuzzy-ANP的空管安全风险评估模型。以某空管单位为例进行实证分析,通过计算评价指标权重,找到影响空管安全风险的关键指标。结果表明,影响该空管单位安全的主要因素为管理标准效能、员工培训次数和人员语言及交流沟通状况等,该空管单位应重点改善这3个因素并兼顾其他影响因素。研究表明,Fuzzy-ANP分析法有助于确定安全风险评估的重点。