基于强化学习的航空器机场智能静态路径规划

随着人工智能迅速发展以及“智慧机场”的提出,研究人工智能在机场如何有效地辅助机场管制人员,驾驶员指挥航空器在地面滑行具有重要意义。本文提出一种基于强化学习的滑行路径规划方法,构建航空器机场地面强化学习移动模型,并以海口美兰机场为案例采用 Python 内置工具包 Tkinter 进行场面仿真;在此基础上,考虑机场航空器滑行规则,采用 Off-Policy 中 Q-Learning 算法求解贝尔曼方程,实现航空器在 Model-based 环境中进行静态路径规划。结果表明：本文所提方法能够实现停机位到跑道出口智能静态路径规划     

基于小波包分析与多核学习的滚动轴承故障诊断

为了更准确地诊断滚动轴承故障,提出了一种基于小波包分析与多核学习的滚动轴承故障诊断方法.该方法首先对振动信号进行3层小波包分解,将振动信号分解为不同频带的信号,提取各频带的相对能量特征,构建特征向量;然后采用多核学习算法从训练样本集中学习核函数与分类器;最后使用训练出的分类器识别滚动轴承故障类型.为了验证方法的有效性,进行了滚动轴承故障诊断实验,实验结果表明该方法的故障诊断准确率达到98.25%,与传统的基于小波包与支持向量机的滚动轴承故障诊断方法相比,其故障诊断准确率更高,同时由于避免了核函数的选择问题,该方法更便于实际应用.      

Probing the origin of the iron Kα line around stellar and supermassive black holes using X-ray polarimetry

Asymmetric, broad iron lines are a common feature in the X-ray spectra of both X-ray binaries (XRBs) and type-1 Active Galactic Nuclei (AGN). It was suggested that the distortion of the Fe Kα emission results from Doppler and relativistic effects affecting the radiative transfer close to the strong gravitational well of the central compact object: a stellar mass black hole (BH) or neutron star (NS) in the case of XRBs, or a super massive black hole (SMBH) in the case of AGN. However, alternative approaches based on reprocessing and transmission of radiation through surrounding media also attempt to explain the line broadening. So far, spectroscopic and timing analyzes have not yet convinced the whole community to discriminate between the two scenarios. Here we study to which extent X-ray polarimetric measurements of black hole X-ray binaries (BHXRBs) and type-1 AGN could help to identify the possible origin of the line distortion. To do so, we report on recent simulations obtained for the two BH flavors and show that the proposed scenarios are found to behave differently in polarization degree and polarization angle. A relativistic origin for the distortion is found to be more probable in the context of BHXRBs, supporting the idea that the same mechanism should lead the way also for AGN. We show that the discriminating polarization signal could have been detectable by several X-ray polarimetry missions proposed in the past.     

磁悬浮飞轮微振动特性及其主动振动控制方法研究

为了进一步减小磁悬浮飞轮的振动力和力矩,建立并分析了一种特殊结构的磁悬浮飞轮的微振动模型,并利用微振动测量平台、数据采集分析硬件和软件,通过试验测量了磁悬浮飞轮6个自由度的振动力和力矩.分析其时域特性和频域特性,其振动特性图(瀑布图)显示了径向两个平动方向X和Y的振动力主要是同频分量、倍频分量以及模态量,其中同频分量较为明显.利用开闭环自适应陷波,分别对X、Y两个方向的振动力进行主动振动控制,取得了较好的控制效果,使得两个方向的振动力的同频量显著下降.     

激光有源干扰的防御措施

激光有源干扰是目前光电干扰领域发展的热点,如何对其实现成功防御是一个重要课题。主要讨论了激光有源干扰的各种防御措施,重点是激光测距机和半主动激光制导武器的抗干扰措施、激光防护器材的防护原理以及新体制导弹的强激光防护技术。     

压电自适应桁架结构主动控制模型及实验

为提高结构对外部环境的抗干扰能力,构造了压电柔性自适应桁架结构,并对其主动控制进行了研究.由传感器、作动器与柔性梁组成压电自适应桁架结构.基于自适应结构的机电耦合理论,在测量位移的情况下,采用改进的二次积分力反馈控制方法研究了空间压电柔性自适应桁架结构的振动主动控制问题.建立了压电柔性自适应桁架结构主动控制实验系统,并对这类自适应结构进行了实时计算机振动主动控制实验研究.实验研究表明柔性自适应桁架结构能够改善结构的动力学特性,对外界的干扰具有良好的自适应性.     

利用神经元拓展正则极端学习机预测时间序列

为实现对于时间序列预测数据的准确预测,提出一种神经元拓展正则极端学习机(NERELM,Neuron-Expanding Regularized Extreme Learning Machine),并研究了其在时间序列预测中的应用.NERELM根据结构风险最小化原理权衡经验风险与结构风险,以逐次拓展隐层神经元的方式自动确定最佳的网络结构,以避免传统神经网络训练过程中需人为确定网络结构的弊端.应用于时间序列的仿真结果表明:NERELM可有效实现对于RELM最佳网络结构的自动确定,具有预测精度高与计算速度快的优点.      

LEVEL DECISION-MAKING FOR AERO-ENGINE MODULES BASED ON INCREMENTAL KNOWLEDGE LEARNING

The maintenance of an aero-engine usually includes three levels, and the maintenance cost and period greatly differ depending on the different maintenance levels. To plan a reasonable maintenance budget program, airlines would like to predict the maintenance level of aero-engine before repairing in terms of performance parame- ters, which can provide more economic benefits. The maintenance level decision rules are mined using the histori- cal maintenance data of a civil aero-engine based on the rough set theory, and a variety of possible models of upda- ting rules produced by newly increased maintenance cases added to the historical maintenance case database are in- vestigated by the means of incremental machine learning. The continuously updated rules can provide reasonable guidance suggestions for engineers and decision support for planning a maintenance budget program before repai- ring. The results of an example show that the decision rules become more typical and robust, and they are more accurate to predict the maintenance level of an aero-engine module as the maintenance data increase, which illus- trates the feasibility of the represented method.     

基于预测扭矩前馈的涡轴发动机内模控制方法

基于内模原理设计了涡轴发动机功率涡轮转速控制器.针对主旋翼扭矩变化对功率涡轮转速的干扰,提出了一种基于极端学习机的扭矩预测方法.极端学习机训练基于动态仿真数据,其输入通过相关分析获得.基于内模原理的功率涡轮转速控制器采用极点配置的设计方法,将输入信号的内模直接加入控制器,实现鲁棒跟踪.扭矩前馈采用比例微分(PD)控制策略,实现对发动机负载变化干扰的有效补偿.数字仿真结果表明:极端学习机扭矩预测精度高,扭矩相对误差小于1.5‰,与不加前馈控制相比,所提出的控制方法减小了机动飞行过程中功率涡轮转速的超调或下垂30%以上.