As the risks associated with air turbulence are intensified by climate change and the growth of the aviation industry,it has become imperative to monitor and mitigate these threats to ensure civil aviation safety.The ...As the risks associated with air turbulence are intensified by climate change and the growth of the aviation industry,it has become imperative to monitor and mitigate these threats to ensure civil aviation safety.The eddy dissipation rate(EDR)has been established as the standard metric for quantifying turbulence in civil aviation.This study aims to explore a universally applicable symbolic classification approach based on genetic programming to detect turbulence anomalies using quick access recorder(QAR)data.The detection of atmospheric turbulence is approached as an anomaly detection problem.Comparative evaluations demonstrate that this approach performs on par with direct EDR calculation methods in identifying turbulence events.Moreover,comparisons with alternative machine learning techniques indicate that the proposed technique is the optimal methodology currently available.In summary,the use of symbolic classification via genetic programming enables accurate turbulence detection from QAR data,comparable to that with established EDR approaches and surpassing that achieved with machine learning algorithms.This finding highlights the potential of integrating symbolic classifiers into turbulence monitoring systems to enhance civil aviation safety amidst rising environmental and operational hazards.展开更多
Flight data of a twin-jet transport aircraft in revenue flight are analyzed for potential safety problems. Data from the quick access recorder （QAR） are first filtered through the kinematic compatibility analysis. T...Flight data of a twin-jet transport aircraft in revenue flight are analyzed for potential safety problems. Data from the quick access recorder （QAR） are first filtered through the kinematic compatibility analysis. The filtered data are then organized into longitudinal- and lateral-directional aerodynamic model data with dynamic ground effect. The dynamic ground effect requires the radio height and sink rate in the models. The model data are then refined into numerical models through a fuzzy logic algorithm without data smoothing in advance. These numerical models describe nonlinear and unsteady aerodynamics and are used in nonlinear flight dynamics simulation. For the jet transport under study, it is found that the effect of crosswind is significant enough to excite the Dutch roll motion. Through a linearized analysis in flight dynamics at every instant of time, the Dutch roll motion is found to be in nonlinear oscillation without clear damping of the amplitude. In the analysis, all stability derivatives vary with time and hence are nonlinear functions of state variables. Since the Dutch roll motion is not damped despite the fact that a full-time yaw damper is engaged, it is concluded that the design data for the yaw damper is not sufficiently realistic and the contribution of time derivative of sideslip angle to damping should be considered. As a result of nonlinear flight simulation, the vertical wind acting on the aircraft is estimated to be mostly updraft which varies along the flight path before touchdown. Varying updraft appears to make the descent rate more difficult to control to result in a higher g-load at touchdown.展开更多
针对目前飞机离地姿态异常的监控依赖单一参数超限探测、缺乏多参数组合异常检测的问题,提出了一种基于近邻搜索空间提取的局部异常因子算法(Isolation-based Data Extracting Local Outlier Factor,IDELOF)的飞机离地姿态异常检测方法...针对目前飞机离地姿态异常的监控依赖单一参数超限探测、缺乏多参数组合异常检测的问题,提出了一种基于近邻搜索空间提取的局部异常因子算法(Isolation-based Data Extracting Local Outlier Factor,IDELOF)的飞机离地姿态异常检测方法。首先,选取空速、俯仰角、滚转角作为飞机离地姿态特征参数,运用基于隔离思想的近邻搜索空间提取方法进行数据降维提取,降低计算复杂度;其次,利用局部异常因子算法对提取后的数据进行异常检测,识别多参综合异常;然后,基于国内某航空公司A319机队297个航班的快速存取记录器(Quick Access Recorder,QAR)数据,验证了模型对单一参数异常和多参综合异常检测结果的有效性;最后,对模型结果的正异常分布特征及可解释性进行分析,分别阐述了八种异常情况出现的主要原因,为飞行安全风险防控提供了深入的数据支持。展开更多
基金supported by the Meteorological Soft Science Project(Grant No.2023ZZXM29)the Natural Science Fund Project of Tianjin,China(Grant No.21JCYBJC00740)the Key Research and Development-Social Development Program of Jiangsu Province,China(Grant No.BE2021685).
文摘As the risks associated with air turbulence are intensified by climate change and the growth of the aviation industry,it has become imperative to monitor and mitigate these threats to ensure civil aviation safety.The eddy dissipation rate(EDR)has been established as the standard metric for quantifying turbulence in civil aviation.This study aims to explore a universally applicable symbolic classification approach based on genetic programming to detect turbulence anomalies using quick access recorder(QAR)data.The detection of atmospheric turbulence is approached as an anomaly detection problem.Comparative evaluations demonstrate that this approach performs on par with direct EDR calculation methods in identifying turbulence events.Moreover,comparisons with alternative machine learning techniques indicate that the proposed technique is the optimal methodology currently available.In summary,the use of symbolic classification via genetic programming enables accurate turbulence detection from QAR data,comparable to that with established EDR approaches and surpassing that achieved with machine learning algorithms.This finding highlights the potential of integrating symbolic classifiers into turbulence monitoring systems to enhance civil aviation safety amidst rising environmental and operational hazards.
基金Foundation item： National Natural Science Foundation of China （60832012）
文摘Flight data of a twin-jet transport aircraft in revenue flight are analyzed for potential safety problems. Data from the quick access recorder （QAR） are first filtered through the kinematic compatibility analysis. The filtered data are then organized into longitudinal- and lateral-directional aerodynamic model data with dynamic ground effect. The dynamic ground effect requires the radio height and sink rate in the models. The model data are then refined into numerical models through a fuzzy logic algorithm without data smoothing in advance. These numerical models describe nonlinear and unsteady aerodynamics and are used in nonlinear flight dynamics simulation. For the jet transport under study, it is found that the effect of crosswind is significant enough to excite the Dutch roll motion. Through a linearized analysis in flight dynamics at every instant of time, the Dutch roll motion is found to be in nonlinear oscillation without clear damping of the amplitude. In the analysis, all stability derivatives vary with time and hence are nonlinear functions of state variables. Since the Dutch roll motion is not damped despite the fact that a full-time yaw damper is engaged, it is concluded that the design data for the yaw damper is not sufficiently realistic and the contribution of time derivative of sideslip angle to damping should be considered. As a result of nonlinear flight simulation, the vertical wind acting on the aircraft is estimated to be mostly updraft which varies along the flight path before touchdown. Varying updraft appears to make the descent rate more difficult to control to result in a higher g-load at touchdown.
文摘针对目前飞机离地姿态异常的监控依赖单一参数超限探测、缺乏多参数组合异常检测的问题,提出了一种基于近邻搜索空间提取的局部异常因子算法(Isolation-based Data Extracting Local Outlier Factor,IDELOF)的飞机离地姿态异常检测方法。首先,选取空速、俯仰角、滚转角作为飞机离地姿态特征参数,运用基于隔离思想的近邻搜索空间提取方法进行数据降维提取,降低计算复杂度;其次,利用局部异常因子算法对提取后的数据进行异常检测,识别多参综合异常;然后,基于国内某航空公司A319机队297个航班的快速存取记录器(Quick Access Recorder,QAR)数据,验证了模型对单一参数异常和多参综合异常检测结果的有效性;最后,对模型结果的正异常分布特征及可解释性进行分析,分别阐述了八种异常情况出现的主要原因,为飞行安全风险防控提供了深入的数据支持。
