Time delay compensation in lateral-directional flight control systems at high angles of attack

The previous studies of time delay compensation in flight control systems are all based on the conventional aerodynamic derivative model and conducted in longitudinal motions at low angles of attack. In this investigation, the effects of time delay on the lateral-directional stability augmentation system in high-α regime are discussed based on the $\dot{\beta }$ model, which is proposed in our previous work and proved as a more accurate aerodynamic model to reveal the lateral-directional unsteady aerodynamic characteristics at high angles of attack. Both the $\dot{\beta }$ model and the quasi-steady model are used for simulating the effects of time delay on the flying qualities in high-α maneuvers. The comparison between the simulation results shows that the flying qualities are much more sensitive to the mismatch of feedback gains than the state errors caused by time delay. Then a typical adaptive controller based on the conventional dynamic derivative model and a gain-prediction compensator based on $\dot{\beta }$ model are designed to address the time delay in different maneuvers. The simulation results show that the gain-prediction compensator is much simpler and more efficient at high angles of attack. Finally, the gain-prediction compensator is combined with a linearized $\dot{\beta }$ model reference adaptive controller to compensate the adverse effects of very large time delay, which exhibits excellent performance when addressing the extreme conditions at high angles of attack.     

Key Problems in Coordinated Air Combat andMulti-agent Reinforcement Learning

自从协同作战的概念提出后,各军事强国在协同空战领域均取得了重大进展,协同成为提升作战能力的倍增器。近数十年来,作为解决序列问题的现代智能方法,强化学习在各领域高速发展。然而,面对高维变量问题时,传统的单智能体强化学习往往表现不佳,多智能体强化学习算法为解决复杂多维问题提出新的可能。通过对多智能体强化学习算法原理、训练范式与协同空战的适应性进行分析,提出了协同空战与多智能体强化学习的未来发展方向,为更好地把多智能体强化学习应用于协同空战提供思路。     

基于隶属度和LMK-ELM的航空电子部件诊断方法

为提高航空电子部件模块级故障诊断精度，提出一种新的面向"软聚类"的局部多核学习（LMKL）-超限学习机（ELM）离线诊断方法。通过引入模糊C均值聚类对样本空间进行模糊划分，挖掘聚类内部多样性的同时，实现了对过学习的抑制；将模糊划分产生的隶属度信息融入LMKL-ELM的优化过程，运用基于初始-对偶混合优化问题的三步优化策略克服了局部核权重二次非凸的问题，在l₁-范数与l₂-范数约束下分别给出了相应的更新方法。将所提方法应用于某型机前端接收机，结果表明：与4种流行的多核诊断方法相比，该方法可有效避免漏警、抑制虚警，在l₁-范数和l₂-范数约束下，其诊断精度比其他方法的平均值分别提升了4.09%和5.13%。     

Predicting lean blow-off of bluffbody stabilized flames based on Damköhler number

Lean Blow-Off(LBO) prediction is important to propulsion system design. In this paper,a hybrid method combining numerical simulation and Da(Damk?hler) model is proposed based on bluffbody stabilized flames. In the simulated reacting flow, Practical Reaction Zone(PRZ) is built based on OH radical concentration, and it is considered to be the critical zone that controls LBO.Da number is obtained based on the volume-averaged parameters of PRZ. The flow time scale(s_f)indicates the residence time of the fresh mixture flowing through the PRZ. It is obtained based on the characteristic length and volume-averaged axial velocity of the PRZ. The chemical time scale(s_c) indicates the shortest time needed to trigger the reaction of the mixture. It is obtained by commercial software CHEMKIN through monitoring the transient variation of the reactor temperature. The result shows that the average Da number under different LBO conditions is 1.135(the Da number under each LBO condition ranges from 0.673 to 1.351). This indicates that the flow time scale and chemical time scale are comparable. The combustion is in a critical state where LBO is easy to occur. With the increase of the fuel mass flow rate(the global fuel/air ratio increases from 0.004761 to 0.01095), s_f increases from 0.001268 s to 0.007249 s, and s_c decreases from 0.00124 s to0.00089 s. Accordingly, Da number increases from 1.023 to 8.145, which shows that the combustion becomes more stable. The above results show that the method proposed in the present study can properly predict the LBO limits of combustors, which provides important technical supports for combustor design and optimization.     

Object-based rice mapping using time-series and phenological data

Remote sensing techniques are often used in mapping rice, but high quality time-series remote sensing data are difficult to obtain due to the cloudy weather of rice growing areas and long satellite revisit interval. As such, rice mapping is usually based on mono-temporal Landsat TM/ETM+ data, which have large uncertainties due to the spectral similarity of different vegetation types. Moreover, conventional pixel-based classification method is unable to meet the required accuracy for rice mapping. Therefore, this study proposes a new strategy for mapping rice in cloud-prone areas using fused data of Landsat-8 OLI time-series and phenological parameters, based on the object-based method. We determine the critical growth stages of paddy rice from observed phenological data and MODIS-NDVI time-series data. The spatial and temporal adaptive reflectance fusion model (STARFM) is used to blend the MODIS and Landsat data to obtain a multi-temporal Landsat-like dataset for classification. Finally, an object-oriented algorithm is used to extract rice paddies from the Landsat-like, time-series dataset. The validation experiments show that the proposed method can provide high accuracy rice mapping, with an overall accuracy of 92.38% and a kappa coefficient of 0.85.     

Advanced ensemble modeling method for space object state prediction accounting for uncertainty in atmospheric density

For objects in the low Earth orbit region, uncertainty in atmospheric density estimation is an important source of orbit prediction error, which is critical for space traffic management activities such as the satellite conjunction analysis. This paper investigates the evolution of orbit error distribution in the presence of atmospheric density uncertainties, which are modeled using probabilistic machine learning techniques. The recently proposed “HASDM-ML,” “CHAMP-ML,” and “MSIS-UQ” machine learning models for density estimation (Licata and Mehta, 2022b; Licata et al., 2022b) are used in this work. The investigation is convoluted because of the spatial and temporal correlation of the atmospheric density values. We develop several Monte Carlo methods, each capturing a different spatiotemporal density correlation, to study the effects of density uncertainty on orbit uncertainty propagation. However, Monte Carlo analysis is computationally expensive, so a faster method based on the Kalman filtering technique for orbit uncertainty propagation is also explored. It is difficult to translate the uncertainty in atmospheric density to the uncertainty in orbital states under a standard extended Kalman filter or unscented Kalman filter framework. This work uses the so-called “consider covariance sigma point (CCSP)” filter that can account for the density uncertainties during orbit propagation. As a test-bed for validation purposes, a comparison between CCSP and Monte Carlo methods of orbit uncertainty propagation is carried out. Finally, using the HASDM-ML, CHAMP-ML, and MSIS-UQ density models, we propose an ensemble approach for orbit uncertainty quantification for four different space weather conditions.     

An ensemble deep learning based shoreline segmentation approach (WaterNet) from Landsat 8 OLI images

Shorelines constantly vary due to natural, urbanization and anthropogenic effects such as global warming, population growth, and environmental pollution. Sustainable monitoring of coastal changes is vital in terms of coastal resource management, environmental preservation and planning. Publicly available Landsat 8 OLI (Operational Land Manager) images provide accurate, reliable, temporal and up-to-date information about coastal areas. Recently, the use of machine learning and deep learning algorithms have become widespread. In this study, we used our public Landsat 8 OLI satellite image dataset to create a majority voting method which is an ensemble automatic shoreline segmentation system (WaterNet) to obtain shorelines automatically. For this purpose, different deep learning architectures have been utilized namely as Standard U-Net, Dilated U-Net, Fractal U-Net, FC-DenseNet, and Pix2Pix. Also, we have suggested a novel framework to create labeling data from OpenStreetMap service to create a unique dataset called YTU-WaterNet. According to the results, IoU and F1 scores have been calculated as 99.59% and 99.79% for the WaterNet. The results indicate that the WaterNet method outperforms other methods in terms of shoreline extraction from Landsat 8 OLI satellite images.     

基于机器学习的导弹干扰试验效果评估实证研究

针对复杂电磁环境下导弹干扰试验影响因素众多,难以量化,试验数据采集困难以及实验数据中普遍存在类不平衡等问题,基于机器学习创建导弹试验干扰效果评估模型,采用随机森林、支持向量机、朴素贝叶斯、多层感知机等常见模型对导弹试验干扰效果进行评估。特别针对小数据样本中的类不平衡问题提出 2阶段分类模型,采用过采样方式解决类不平衡问题并采用随机森林进行分类。基于开源的导弹干扰效果评估数据,通过实证研究说明,基于过采样的随机森林模型在干扰效果评估问题中具有较强的泛化能力和鲁棒性,在 AUC指标上,该模型比多层感知机模型在中位数上最多提高 60%,建议在后续的试验中采用该模型进行导弹干扰效果评估。     

空气动力二阶核函数辨识方法

采用截断三阶Volterra级数模型来研究空气动力二阶核函数的辨识问题,选取一簇正交化的切比雪夫多项式对二阶核函数进行参数化处理,并将非参数辨识问题转化成参数辨识问题。相比于其他方法,本文模型能有效降低对激励信号幅值的敏感程度,保证辨识出的核函数具有较好的保真度;只针对三阶Volterra降阶模型中的一阶、二阶核函数进行辨识,即可提升原系统一阶、二阶核函数的辨识精度,却不会显著增加辨识过程的工作量;参数化辨识方法属于整体性辨识,根据已有的部分数据对(输入、输出数据)就能完成系统辨识,且能达到较好的辨识精度,从而有效地减少了执行计算流体力学(CFD)代码程序的总次数,节约了大量的时间成本。算例表明,与目前流行的非参数化方法相比,本文提出的切比雪夫函数辨识方法,精度上达到预期要求,辨识过程消耗的CFD总时间量至少可降低一个数量级。     

交错级数的审敛法

本文给出交错级数及双项交错级数的一种类型的审敛法，并分别给出判定交错级数及双项交错级数绝对收敛的一种方法。