基于神经网络的空中交通管制决策支持系统

随着民用航空运输的迅速发展,为满足更大的需求,减少管制人员的工作压力和工作量,设计了一个实时的空中交通管制决策支持系统。系统按照决策支持系统理论框架搭建,包括数据库、模型库、方法库、知识库和人机界面,其中主要模型和方法：空域流量预测模块,空域状态识别模块和冲突解决方案产生模块利用神经网络技术来实现,其中空域流量预测模块利用模糊神经网络技术。系统通过与近期真实数据相结合,进行仿真,取得较好的效果。     

Objective Job Difficulty,Behavioural Response,and Sector Characteristics in Air Route Traffic Control Centres∗

Abstract

Two thousand observations on 47 radar sectors in Boston and New York were used to determine the principal behavioural stressors in the air traffic control environment. Predictor variables included peak traffic. mean airspeed, sector area, sector type, radio-communication time, and theoretically derived control load factors.

Expert observers rated the degree of activity and behavioural arousal of ATCs working the 47 radar sectors at the same time the objective measures were made. These ‘pace’ ratings were significantly related to peak traffic count and duration of radio-communications.

The control load factors were not related to behavioural responses. Statistical analyses indicated several refinements for the definition and measurement of the control load factors, For example, airspace control load was reliably estimated by sector type and number of transitioning planes, while co-ordination control load was most appropriately estimated by duration of radio-communications

These results suggested that estimations of workload may be made by a relatively few objective measures, and that at least one estimate of individual's behavioural responses, i.e.. pace ratings, can be predicted by peak traffic counts.     

Solution of sectorization problems for an air traffic control area. I. Basic principles and questions of airspace sectorization and its formalization as an optimization problem

Problems of airspace sectorization of air traffic areas are studied as airspace design problems. The sectorization problem consists in optimal (from the point of view of controller workload) space and time partitioning of the area of responsibility of a regional center of air traffic management into controller sectors with account of existing route structure and dynamics of air traffic intensity and composition. In this paper, the following problems are discussed: the role of airspace design in terms of the next-generation air traffic management system, the analysis of applied approaches, methods, and algorithms for solution of the studied problem, the basic principles of sectorization, the formulation of the problem of sectorization and the outline of its solution.     

Modeling and predicting mental workload in en route air traffic control: critical review and broader implications

OBJECTIVE: We perform a critical review of research on mental workload in en route air traffic control (ATC). We present a model of operator strategic behavior and workload management through which workload can be predicted within ATC and other complex work systems. BACKGROUND: Air traffic volume is increasing worldwide. If air traffic management organizations are to meet future demand safely, better models of controller workload are needed. METHOD: We present the theoretical model and then review investigations of how effectively traffic factors, airspace factors, and operational constraints predict controller workload. RESULTS: Although task demand has a strong relationship with workload, evidence suggests that the relationship depends on the capacity of the controllers to select priorities, manage their cognitive resources, and regulate their own performance. We review research on strategies employed by controllers to minimize the control activity and information-processing requirements of control tasks. CONCLUSION: Controller workload will not be effectively modeled until controllers' strategies for regulating the cognitive impact of task demand have been modeled. APPLICATION: Actual and potential applications of our conclusions include a reorientation of workload modeling in complex work systems to capture the dynamic and adaptive nature of the operator's work. Models based around workload regulation may be more useful in helping management organizations adapt to future control regimens in complex work systems.     

Objective Workload and Behavioural Response in Airport Radar Control Rooms

Previous research indicated that peak traffic and the duration of radio-communications were good predictors of behavioural response of air traffic controllers working in air route traffic control centres. In this study we investigated if these two measures of workload were generalisable to controllers (ATCs) working in radar facilities serving major airports. 3,110 observations were made on radar sectors at the 13 major radar control rooms in the U.S.A. A large number of air traffic variables and communication tasks were measured. Behavioural ratings were made by expert-observer ATC's. The results replicated previous findings that peak traffic and the duration of radio-communications functioned as behavioural stressors. Time monitoring and stand-by time also were found to predict behavioural responses. Careful consideration of these and other results led to the conclusion that peak traffic is the most generalisable environmental stressor for ATC's behaviour whereas the other workload measures are more correctly viewed as concomitants of the demand characteristics of ATC work.     

图切割快速生成扇区的蚁群算法

扇区划分是平衡管制员工作负荷、提升空域通行能力的有效技术措施.采用Voronoi图自顶向下切割空域的方法具有自动保证扇区凸性、连通性和压缩性的特性,但计算时间过长.根据航迹状态计算工作负荷,构建了Voronoi图自顶向下切割空域模型,设计了动态步长蚁群搜索算法.测试结果表明,在太原高空划分成4个扇区的情况下,与MC-C...     

空管自动化系统应用与维护探索

近年来,随着我国民用航空运输业的飞速发展和军航作训范围、数量、规模的日益扩大,对空域资源的使用变得越来越紧张,已经频繁出现因空中交通管制原因造成飞机“飞不出去”或“降不下来”等飞行矛盾.空管自动化系统是维持空中交通秩序、实现有效的空中交通安全管理、确保空中交通快速有序流动的指挥核心.以某军航空管“十五”管制中心系统为例,从使用与维护两个方面对其进行探讨,以期能使用好和维护好此系统.     

From trees to forest: relational complexity network and workload of air traffic controllers

In this paper, we propose a relational complexity (RC) network framework based on RC metric and network theory to model controllers' workload in conflict detection and resolution. We suggest that, at the sector level, air traffic showing a centralised network pattern can provide cognitive benefits in visual search and resolution decision which will in turn result in lower workload. We found that the network centralisation index can account for more variance in predicting perceived workload and task completion time in both a static conflict detection task (Study 1) and a dynamic one (Study 2) in addition to other aircraft-level and pair-level factors. This finding suggests that linear combination of aircraft-level or dyad-level information may not be adequate and the global-pattern-based index is necessary. Theoretical and practical implications of using this framework to improve future workload modelling and management are discussed.     

Dynamic network flow model for short-term air traffic flow management

Since it is safer and less expensive to absorb delays on the ground, many models have been developed to assign ground holding delays optimally in the general network of airports, so that the total (ground plus airborne) delay costs of all fights are minimized. Still, the undeniable fact remains that airborne delays cannot be totally avoided. When there are airborne holds, such as when the local airspace capacity has a sudden decrease due to bad weather or other unpredicted disruptions, it is important to quickly minimize the costs of airborne holds. Much research has been conducted to explore ways to minimize airborne holds. Motivated by this, after analyzing the network structure of air traffic control areas and the dynamic nature of air traffic flow, this paper presents a model based on multicommodity dynamic network flow for short-term air traffic flow management. The model was validated by practical data from the Beijing ATC Center of the Civil Aviation Administration of China (CAAC).     

Development and application of a human error identification tool for air traffic control

This paper outlines a human error identification (HEI) technique called TRACEr--technique for the retrospective and predictive analysis of cognitive errors in air traffic control (ATC). The paper firstly considers the need for an HEI tool in ATC, and key requirements for the technique are noted. The technique, which comprises a number of inter-related taxonomies, based around a simple cognitive framework, is then described. A study concerning a real-world application of TRACEr is outlined-the evaluation of several options for reduced separation minima in unregulated UK airspace. In this study, TRACEr was used predictively and retrospectively, looking forward to pre-empt potential problems and looking back to learn from experience. The paper concludes that TRACEr is a valuable aid to design, development and operations in UK ATC, and has indeed been used as a basis for further applications in ATC both in Europe and the USA.     

Using random forests to diagnose aviation turbulence

Atmospheric turbulence poses a significant hazard to aviation, with severe encounters costing airlines millions of dollars per year in compensation, aircraft damage, and delays due to required post-event inspections and repairs. Moreover, attempts to avoid turbulent airspace cause flight delays and en route deviations that increase air traffic controller workload, disrupt schedules of air crews and passengers and use extra fuel. For these reasons, the Federal Aviation Administration and the National Aeronautics and Space Administration have funded the development of automated turbulence detection, diagnosis and forecasting products. This paper describes a methodology for fusing data from diverse sources and producing a real-time diagnosis of turbulence associated with thunderstorms, a significant cause of weather delays and turbulence encounters that is not well-addressed by current turbulence forecasts. The data fusion algorithm is trained using a retrospective dataset that includes objective turbulence reports from commercial aircraft and collocated predictor data. It is evaluated on an independent test set using several performance metrics including receiver operating characteristic curves, which are used for FAA turbulence product evaluations prior to their deployment. A prototype implementation fuses data from Doppler radar, geostationary satellites, a lightning detection network and a numerical weather prediction model to produce deterministic and probabilistic turbulence assessments suitable for use by air traffic managers, dispatchers and pilots. The algorithm is scheduled to be operationally implemented at the National Weather Service’s Aviation Weather Center in 2014.     

The dynamic predictive power of company comparative networks for stock sector performance

As economic integration and business connections increase, companies actively interact with each other in the market in cooperative or competitive relationships. To understand the market network structure with company relationships and to investigate the impacts of market network structure on stock sector performance, we propose the construct of a company comparative network based on public media data and sector interaction metrics based on the company network. All the market network structure metrics are integrated into a vector autoregression model with stock sector return and risk. Several findings demonstrate the dynamic relationships that exist between sector interactions and sector performance. First, sector interaction metrics constructed based on company networks are significant leading indicators of sector performance. Interestingly, the interactions between sectors have greater predictive power than those within sectors. Second, compared with the company closeness network, the company comparative network, which labels the cooperative or competitive relationships between companies, is a better construct to understand and predict sector interactions and performance. Third, competitive company interactions between sectors impact sector performance in a slower manner than cooperative company interactions. The findings enrich financial studies regarding asset pricing by providing additional explanations of company/sector interactions and insights into company management using industry-level strategies.     

基于多数据源的管制员工作负荷自动统计与分析系统

随着青岛空域飞行流量的不断增加,管制员的工作负荷不断增大.管制员工作负荷的量化及班组资源的合理分配已经成为制约扇区容量的重要因素之一.本文结合民航青岛空管站在实际运行和新增扇区工作中遇到的问题,讨论影响管制员工作负荷的复杂性因素,提出管制负荷计算模型.通过充分利用现有的航班、通话等客观数据,依据客观反映我站管制员工作负荷的计算模型,由计算机生成不同扇区的工作负荷指数,并根据电子值班日志岗位计时数据对每一位管制员的工作负荷进行量化与统计,从而为我站关于扇区容量评估、运行分析、班组资源分配、人员绩效等问题提供决策支持.文章最后对计算结果进行了分析验证,进一步讨论该模型的可行性和存在的问题,并对论文的成果进行总结和展望.     

On synthetic workloads for multiplayer online games: a methodology for generating representative shooter game workloads

We present approaches to the generation of synthetic workloads for benchmarking multiplayer online gaming infrastructures. Existing techniques, such as mobility or traffic models, are often either too simple to be representative for this purpose or too specific for a particular network structure. Desirable properties of a workload are reproducibility, representativeness, and scalability to any number of players. We analyze different mobility models and AI-based workload generators. Real gaming sessions with human players using the prototype game Planet PI4 serve as a reference workload. Novel metrics are used to measure the similarity between real and synthetic traces with respect to neighborhood characteristics. We found that, although more complicated to handle, AI players reproduce real workload characteristics more accurately than mobility models.     

基于遗传算法组合预测模型的空域流量预测系统构建

航班总量的持续增长使得航班安全保障的压力不断加大。在空域资源有限、航空管制工作繁重的大型国际机场,航班动态信息的准确、可靠性将为制定有效地管制调配措施提供有力的依据。为了准确预测特定区域中某个航路点在某一时间段的航班流量,给管制人员提供参考,便于提前灵活、合理地制定管制策略,避免空域资源浪费,为各级决策部门制定发展战略与规划提供重要依据。基于不同航班流量信息源建立组合预测模型,通过遗传算法对组合模型的权重值进行优化,并根据西安管制区域构建出了空域流量预测系统的设计构架。     

Datalink in air traffic management: Human factors issues in communications

This paper examines issues underpinning the potential move in aviation away from real speech radiotelephony (R/T) communications towards datalink communications involving text and synthetic speech communications. Using a novel air traffic control (ATC) task, two experiments are reported. Experiment 1 compared the use of speech and text while Experiment 2 compared the use of real and synthetic speech communications. Results indicated that generally there were no significant differences between speech and text communications and that either type could be used without any main effects on performance. However, a number of specific differences were observed across the different phases of the scenarios indicating that workload levels may be more varied when speech communications are used. Experiment 2 illustrated that participants placed a greater level of trust in real speech than synthetic speech, and trusted true communications more than false communications (regardless of whether they were real or synthetic voices). The findings are considered in terms of datalink initiatives for future air traffic management, the importance placed on real speech R/T communications, and the need to develop more natural synthetic speech in this application area.     

一种网络流量预测的小波神经网络模型

结合小波变换和人工神经网络的优势,建立一种网络流量预测的小波神经网络模型。首先对流量时间序列进行小波分解,得到小波变换尺度系数序列和小波系数序列,以系数序列和原来的流量时间序列分别作为模型的输入和输出,构造人工神经网络并且加以训练。用实际网络流量对该模型进行验证,结果表明,该模型具有较高的预测效果。     

遗传算法优化BP 神经网络的短时交通流混沌预测

为了提高BP神经网络预测模型对混沌时间序列的预测准确性,提出了一种基于遗传算法优化BP神经网络的改进混沌时间序列预测方法.利用遗传算法优化BP神经网络的权值和阈值,然后训练BP神经网络预测模型以求得最优解,并将该预测方法应用到几个典型混沌时间序列和实测短时交通流时间序列进行有效性验证.仿真结果表明,该方法对典型混沌时间序列和短时交通流具有较好的非线性拟合能力和更高的预测准确性.