For the accurate description of aerodynamic characteristics for aircraft,a wavelet neural network (WNN) aerodynamic modeling method from flight data,based on improved particle swarm optimization (PSO) algorithm with i...For the accurate description of aerodynamic characteristics for aircraft,a wavelet neural network (WNN) aerodynamic modeling method from flight data,based on improved particle swarm optimization (PSO) algorithm with information sharing strategy and velocity disturbance operator,is proposed.In improved PSO algorithm,an information sharing strategy is used to avoid the premature convergence as much as possible;the velocity disturbance operator is adopted to jump out of this position once falling into the premature convergence.Simulations on lateral and longitudinal aerodynamic modeling for ATTAS (advanced technologies testing aircraft system) indicate that the proposed method can achieve the accuracy improvement of an order of magnitude compared with SPSO-WNN,and can converge to a satisfactory precision by only 60 120 iterations in contrast to SPSO-WNN with 6 times precocities in 200 times repetitive experiments using Morlet and Mexican hat wavelet functions.Furthermore,it is proved that the proposed method is feasible and effective for aerodynamic modeling from flight data.展开更多
Flight data anomaly detection plays an imperative role in the safety and maintenance of unmanned aerial vehicles(UAVs).It has attracted extensive attention from researchers.However,the problems related to the difficul...Flight data anomaly detection plays an imperative role in the safety and maintenance of unmanned aerial vehicles(UAVs).It has attracted extensive attention from researchers.However,the problems related to the difficulty in obtaining abnormal data,low model accuracy,and high calculation cost have led to severe challenges with respect to its practical applications.Hence,in this study,firstly,several UAV flight data simulation softwares are presented based on a brief presentation of the basic concepts of anomalies,the contents of UAV flight data,and the public datasets for flight data anomaly detection.Then,anomaly detection technologies for UAV flight data are comprehensively reviewed,including knowledge-based,model-based,and data-driven methods.Next,UAV flight data anomaly detection applications are briefly described and analyzed.Finally,the future trends and directions of UAV flight data anomaly detection are summarized and prospected,which aims to provide references for the following research.展开更多
This paper introduces the background, aim, experimental design, configuration and data processing for an airborne test flight of the HY-2 Microwave scatterometer(HSCAT). The aim was to evaluate HSCAT performance and a...This paper introduces the background, aim, experimental design, configuration and data processing for an airborne test flight of the HY-2 Microwave scatterometer(HSCAT). The aim was to evaluate HSCAT performance and a developed data processing algorithm for the HSCAT before launch. There were three test flights of the scatterometer, on January 15, 18 and 22, 2010, over the South China Sea near Lingshui, Hainan. The test flights successfully generated simultaneous airborne scatterometer normalized radar cross section(NRCS), ASCAT wind, and ship-borne-measured wind datasets, which were used to analyze HSCAT performance. Azimuthal dependence of the NRCS relative to the wind direction was nearly cos(2w), with NRCS minima at crosswind directions, and maxima near upwind and downwind. The NRCS also showed a small difference between upwind and downwind directions, with upwind crosssections generally larger than those downwind. The dependence of airborne scatterometer NRCS on wind direction and speed showed favorable consistency with the NASA scatterometer geophysical model function(NSCAT GMF), indicating satisfactory HSCAT performance.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
针对先进高性能飞行器对高精度大气数据的测控需求,研发设计了一套适用于亚声速飞行器的嵌入式大气数据传感(flush air data sensing,FADS)系统。该系统首先基于数值建模技术建立了FADS系统模型的压力数据库,并针对建模数据精度及风洞...针对先进高性能飞行器对高精度大气数据的测控需求,研发设计了一套适用于亚声速飞行器的嵌入式大气数据传感(flush air data sensing,FADS)系统。该系统首先基于数值建模技术建立了FADS系统模型的压力数据库,并针对建模数据精度及风洞试验校准数据分析了Ma=0.2~0.4对应的压力误差限;其次,开发了攻角实时解算算法,并集成到工程原理样机中;最后基于风洞试验和飞行试验对FADS系统的实时解算算法及样机进行了系统评估,并通过事后模型算法对攻角进行重新解算以评估攻角实时解算算法的可靠性。结果表明:(1)与机载惯性导航系统等其他独立测试系统解算的数据相比,飞行试验中FADS系统采用的攻角实时解算方法精度整体较好,攻角误差小于1°,在关键段小于0.5°;基于不同模型建立的FADS系统攻角解算方法得到的攻角数值基本一致,证实了开发的实时解算算法的可靠性。(2)基于风洞试验及飞行试验数据对算法误差限的考核结果显示,飞行试验初始阶段实时解算的攻角值产生波动是压力输入波动误差限较大造成的,高空低速时的压力波动幅值大是实时解算攻角值偏差较大的主要原因;建立的FADS系统的攻角解算方法在算法误差限范围内的压力波动对攻角解算值影响较小,但超过算法误差限的压力波动对攻角解算值影响显著。高空低速飞行器FADS系统对测压传感器精度水平及工程实施水平要求较高,在实际工程应用中应尽量保证测压传感器的精度水平。展开更多
针对亚声速飞行器对高精度飞行参数的测控需求,研发了一套亚声速嵌入式大气数据传感(flush air data sensing,FADS)系统,集成工程样机,并通过风洞试验及飞行试验进行系统考核评估。基于计算流体动力学(computational fluid dynamics,CFD...针对亚声速飞行器对高精度飞行参数的测控需求,研发了一套亚声速嵌入式大气数据传感(flush air data sensing,FADS)系统,集成工程样机,并通过风洞试验及飞行试验进行系统考核评估。基于计算流体动力学(computational fluid dynamics,CFD)方法首先建立FADS系统压力数据库,并通过风洞试验考核了模型算法在低亚声速时的误差限;其次,集成融合实时解算算法的FADS工程原理样机;最后通过飞行试验考核了工程样机的工程适用性。结果表明:(1)与机载的其他独立测试系统相比,FADS攻角实时解算精度高,攻角偏差≤1°,关键段攻角偏差≤0.5°;事后重建的攻角数据与飞行试验FADS系统实时解算数据一致,证实FADS实时攻角解算方法可靠;(2)风洞及飞行试验校核数据表明,FADS实时攻角输出数据在飞行试验初始段的波动是由输入压力波动较大导致,特别是在高空低速段,输入压力波动幅值超过算法的误差限,导致实时攻角解算数值波动较大;(3)CFD仿真结果表明,输入压力波动位于算法误差限内对攻角输出精度影响较小,超过算法误差限的压力幅值波动对实时攻角输出精度影响极大。高空低速飞行器FADS系统对压力传感器等硬件精度及工程实现水平要求较高,应尽量保证工程实施精度。展开更多
为解决传统检测方法在处理复杂、动态以及数据长度实时变化的飞行轨迹数据时特征提取不准确、检测效率较低的问题,提出一种结合长短时记忆(Long Short-Term Memory, LSTM)网络和支持向量数据描述(Support Vector Data Description, SVDD...为解决传统检测方法在处理复杂、动态以及数据长度实时变化的飞行轨迹数据时特征提取不准确、检测效率较低的问题,提出一种结合长短时记忆(Long Short-Term Memory, LSTM)网络和支持向量数据描述(Support Vector Data Description, SVDD)的无监督异常检测方法。利用LSTM网络提取可变长度飞行轨迹的关键特征,并将其转化为固定长度的序列表示;通过SVDD算法构建多维超球分类器,对正常飞行轨迹进行建模,从而识别潜在异常轨迹。为进一步提升模型性能,引入基于梯度的优化算法(Gradient-Based training algorithm, GB),实现LSTM与SVDD参数的联合训练,大幅度提高检测精度和计算效率。仿真实验结果表明,新提出的基于梯度优化的长短时记忆网络和支持向量数据描述模型(Long Short-Term Memory network and Support Vector Data Description model based on Gradient-Based training algorithm optimization, LSTM-GBSVDD)的飞行轨迹异常检测方法在处理复杂、多变的飞行轨迹异常检测任务中表现出较好的有效性和优越性,有较强的应用前景。展开更多
文摘For the accurate description of aerodynamic characteristics for aircraft,a wavelet neural network (WNN) aerodynamic modeling method from flight data,based on improved particle swarm optimization (PSO) algorithm with information sharing strategy and velocity disturbance operator,is proposed.In improved PSO algorithm,an information sharing strategy is used to avoid the premature convergence as much as possible;the velocity disturbance operator is adopted to jump out of this position once falling into the premature convergence.Simulations on lateral and longitudinal aerodynamic modeling for ATTAS (advanced technologies testing aircraft system) indicate that the proposed method can achieve the accuracy improvement of an order of magnitude compared with SPSO-WNN,and can converge to a satisfactory precision by only 60 120 iterations in contrast to SPSO-WNN with 6 times precocities in 200 times repetitive experiments using Morlet and Mexican hat wavelet functions.Furthermore,it is proved that the proposed method is feasible and effective for aerodynamic modeling from flight data.
基金supported by the National Key R&D Program of China(Grant No.2020YFB1713300)Guizhou Provincial Colleges and Universities Talent Training Base Project(Grant No.[2020]009)+3 种基金Guizhou Province Science and Technology Plan Project(Grant Nos.[2015]4011 and[2017]5788)Guizhou Provincial Department of Education Youth Science and Technology Talent Growth Project(Grant No.[2022]142)the Scientific Research Project for Introducing Talents from Guizhou University(Grant No.(2021)74)the Guizhou Province Higher Education Integrated Research Platform Project(Grant No.[2020]005)。
文摘Flight data anomaly detection plays an imperative role in the safety and maintenance of unmanned aerial vehicles(UAVs).It has attracted extensive attention from researchers.However,the problems related to the difficulty in obtaining abnormal data,low model accuracy,and high calculation cost have led to severe challenges with respect to its practical applications.Hence,in this study,firstly,several UAV flight data simulation softwares are presented based on a brief presentation of the basic concepts of anomalies,the contents of UAV flight data,and the public datasets for flight data anomaly detection.Then,anomaly detection technologies for UAV flight data are comprehensively reviewed,including knowledge-based,model-based,and data-driven methods.Next,UAV flight data anomaly detection applications are briefly described and analyzed.Finally,the future trends and directions of UAV flight data anomaly detection are summarized and prospected,which aims to provide references for the following research.
基金Supported by the National Natural Science Foundation of China(No.41106152)the National Science and Technology Support Program of China(No.2013BAD13B01)+3 种基金the National High Technology Research and Development Program of China(863 Program)(No.2013AA09A505)the International Science&Technology Cooperation Program of China(No.2011DFA22260)the National High Technology Industrialization Project(No.[2012]2083)the Marine Public Projects of China(Nos.201105032,201305032,201105002-07)
文摘This paper introduces the background, aim, experimental design, configuration and data processing for an airborne test flight of the HY-2 Microwave scatterometer(HSCAT). The aim was to evaluate HSCAT performance and a developed data processing algorithm for the HSCAT before launch. There were three test flights of the scatterometer, on January 15, 18 and 22, 2010, over the South China Sea near Lingshui, Hainan. The test flights successfully generated simultaneous airborne scatterometer normalized radar cross section(NRCS), ASCAT wind, and ship-borne-measured wind datasets, which were used to analyze HSCAT performance. Azimuthal dependence of the NRCS relative to the wind direction was nearly cos(2w), with NRCS minima at crosswind directions, and maxima near upwind and downwind. The NRCS also showed a small difference between upwind and downwind directions, with upwind crosssections generally larger than those downwind. The dependence of airborne scatterometer NRCS on wind direction and speed showed favorable consistency with the NASA scatterometer geophysical model function(NSCAT GMF), indicating satisfactory HSCAT performance.
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.
文摘针对先进高性能飞行器对高精度大气数据的测控需求,研发设计了一套适用于亚声速飞行器的嵌入式大气数据传感(flush air data sensing,FADS)系统。该系统首先基于数值建模技术建立了FADS系统模型的压力数据库,并针对建模数据精度及风洞试验校准数据分析了Ma=0.2~0.4对应的压力误差限;其次,开发了攻角实时解算算法,并集成到工程原理样机中;最后基于风洞试验和飞行试验对FADS系统的实时解算算法及样机进行了系统评估,并通过事后模型算法对攻角进行重新解算以评估攻角实时解算算法的可靠性。结果表明:(1)与机载惯性导航系统等其他独立测试系统解算的数据相比,飞行试验中FADS系统采用的攻角实时解算方法精度整体较好,攻角误差小于1°,在关键段小于0.5°;基于不同模型建立的FADS系统攻角解算方法得到的攻角数值基本一致,证实了开发的实时解算算法的可靠性。(2)基于风洞试验及飞行试验数据对算法误差限的考核结果显示,飞行试验初始阶段实时解算的攻角值产生波动是压力输入波动误差限较大造成的,高空低速时的压力波动幅值大是实时解算攻角值偏差较大的主要原因;建立的FADS系统的攻角解算方法在算法误差限范围内的压力波动对攻角解算值影响较小,但超过算法误差限的压力波动对攻角解算值影响显著。高空低速飞行器FADS系统对测压传感器精度水平及工程实施水平要求较高,在实际工程应用中应尽量保证测压传感器的精度水平。
文摘针对亚声速飞行器对高精度飞行参数的测控需求,研发了一套亚声速嵌入式大气数据传感(flush air data sensing,FADS)系统,集成工程样机,并通过风洞试验及飞行试验进行系统考核评估。基于计算流体动力学(computational fluid dynamics,CFD)方法首先建立FADS系统压力数据库,并通过风洞试验考核了模型算法在低亚声速时的误差限;其次,集成融合实时解算算法的FADS工程原理样机;最后通过飞行试验考核了工程样机的工程适用性。结果表明:(1)与机载的其他独立测试系统相比,FADS攻角实时解算精度高,攻角偏差≤1°,关键段攻角偏差≤0.5°;事后重建的攻角数据与飞行试验FADS系统实时解算数据一致,证实FADS实时攻角解算方法可靠;(2)风洞及飞行试验校核数据表明,FADS实时攻角输出数据在飞行试验初始段的波动是由输入压力波动较大导致,特别是在高空低速段,输入压力波动幅值超过算法的误差限,导致实时攻角解算数值波动较大;(3)CFD仿真结果表明,输入压力波动位于算法误差限内对攻角输出精度影响较小,超过算法误差限的压力幅值波动对实时攻角输出精度影响极大。高空低速飞行器FADS系统对压力传感器等硬件精度及工程实现水平要求较高,应尽量保证工程实施精度。
文摘为解决传统检测方法在处理复杂、动态以及数据长度实时变化的飞行轨迹数据时特征提取不准确、检测效率较低的问题,提出一种结合长短时记忆(Long Short-Term Memory, LSTM)网络和支持向量数据描述(Support Vector Data Description, SVDD)的无监督异常检测方法。利用LSTM网络提取可变长度飞行轨迹的关键特征,并将其转化为固定长度的序列表示;通过SVDD算法构建多维超球分类器,对正常飞行轨迹进行建模,从而识别潜在异常轨迹。为进一步提升模型性能,引入基于梯度的优化算法(Gradient-Based training algorithm, GB),实现LSTM与SVDD参数的联合训练,大幅度提高检测精度和计算效率。仿真实验结果表明,新提出的基于梯度优化的长短时记忆网络和支持向量数据描述模型(Long Short-Term Memory network and Support Vector Data Description model based on Gradient-Based training algorithm optimization, LSTM-GBSVDD)的飞行轨迹异常检测方法在处理复杂、多变的飞行轨迹异常检测任务中表现出较好的有效性和优越性,有较强的应用前景。
