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.      

深空探测器被动式高精度多普勒测量方法与应用

针对深空探测器的单程多普勒测量需求,研究了被动式高精度多普勒测量方法及其实现技术。该方法基于探测器测控信标残留载波等点频信号和VLBI测站高精度氢原子钟频标,构造出与实际接收信号频率接近的参考信号;再通过本地相关处理,完成高精度开环多普勒测量。其特色在于完全不需要精确的先验轨道模型。所开发的专用被动式多普勒测量设备,在国内第一次成功用于欧空局环火星探测器“MEX”的多普勒测定轨试验。探测器X频段信号5s积分的单程多普勒测量精度达到 0.2mm/s ,与欧空局测量水平相当。采用该多普勒测量数据的MEX定轨结果与欧空局精密轨道在数百米至千米量级一致。     

深空通信中高性能低复杂度的QC-LDPC码构造方法

LDPC码字具有优异的性能, 在空间通信中得到广泛应用. 为进一步降低LDPC码构造及编码的复杂度, 给出了一种高性能、低复杂度的QC-LDPC码构造方法. 设计了扩展近似下三角阵(extern Approximate Lower Triangular, eALT)结构的全局矩阵, 通过增加双对角阵结构全局矩阵的列重, 降低差错平底(error floor). 为降低传统循环移位系数选择的复杂度, 提出了一种基于Zig-Zag的移位系数设计方法, 采用数学公式计算循环移位系数, 无需计算机搜索即可完全消除长度为4的短环. 给出了所构造码字线性编码的实现过程. 仿真结果表明, 所提构造方法在保证线性编码复杂度的前提下, 增大了码字间最小距离, 降低了差错平底, 提高了码字性能; 采用结构化的方法设计循环移位系数, 无需计算机搜索即可消除4环, 所构造的码字与CCSDS标准中的码字在性能相近的情况下, 降低了实现的复杂度.      

多径干扰下GPS/INS跟踪环路的一种高斯码相位鉴别器

针对载体在多径信号的影响下,传统码相位鉴别器不能实时有效鉴别出码相位误差,提出一种高斯码相位鉴别器构建方法。在GPS/INS深组合模式中,接收机码相位鉴别器的构建将改变传统设计方法。INS系统利用GPS接收机产生的即时码相位信息,建立INS系统码相位鉴别器,该INS码相位鉴别器用于辅助GPS接收机码相位鉴别器,构建高斯码相位鉴别器,有效降低码相位跟踪误差。仿真结果表明,与传统的码鉴相器相比,高斯码相位鉴别器减小了噪声方差,能有效提高鉴相精度,从而在多径干扰下提高定位精度。     

Aerial-BiSeNet: A real-time semantic segmentation network for high resolution aerial imagery

The aircraft system has recently gained its reputation as a reliable and efficient tool for sensing and parsing aerial scenes. However, accurate and fast semantic segmentation of high-resolution aerial images for remote sensing applications is still facing three challenges: the requirements for limited processing resources and low-latency operations based on aerial platforms, the balance between high accuracy and real-time efficiency for model performance, and the confusing objects with large intra-class variations and small inter-class differences in high-resolution aerial images. To address these issues, a lightweight and dual-path deep convolutional architecture, namely Aerial Bilateral Segmentation Network (Aerial-BiSeNet), is proposed to perform real-time segmentation on high-resolution aerial images with favorable accuracy. Specifically, inspired by the receptive field concept in human visual systems, Receptive Field Module (RFM) is proposed to encode rich multi-scale contextual information. Based on channel attention mechanism, two novel modules, called Feature Attention Module (FAM) and Channel Attention based Feature Fusion Module (CAFFM) respectively, are proposed to refine and combine features effectively to boost the model performance. Aerial-BiSeNet is evaluated on the Potsdam and Vaihingen datasets, where leading performance is reported compared with other state-of-the-art models, in terms of both accuracy and efficiency.     

基于自适应迭代学习的小行星绕飞容错控制

对于小行星绕飞任务的探测器姿态控制问题,已有方法大都考虑了干扰力矩和参数不确定等因素,而忽视了执行器故障情况。针对执行器故障条件下的小行星探测器姿态控制问题,提出了一种基于自适应迭代学习的容错控制方法。所设计的控制器包括两部分：其一针对执行器故障,设计了自适应迭代学习控制器,采用类滑模的思想和自适应迭代学习算法对控制器参数进行调整,进而补偿执行器故障带来的影响,保证系统在控制输出不足情况下的高精度姿态稳定性;其二针对探测器参量变化、外部环境干扰等不确定情况,设计了基于自适应神经网络的迭代学习控制器,采用径向基函数（RadialBasisFunction,RBF）神经网络对系统非线性部分进行逼近,同时对控制器参数进行自适应迭代学习调整,进而保证系统在不确定情况下的动态性能。数值仿真结果表明该控制器能够有效抑制外部环境干扰和内部参数变化带来的不利影响,在执行器部分失效甚至完全失效故障情况下,仍能保证系统的鲁棒性并实现误差在10^-2数量级内的较高姿态控制精度。     

基于高斯过程的机器人自适应抓取策略

在机器人抓取作业时,目标物体的位姿经常发生变化。为了使机器人在运动过程中能够适应物体的位姿变化,提出了一种基于高斯过程的机器人自适应抓取策略。该方法建立了从观测空间到关节空间的映射,使机器人从样本中学习,省去了机器人视觉系统的标定和逆运动学求解。首先,拖动机器人抓取物体,记录物体的观测变量和机器人的关节角度;然后,利用记录的样本训练高斯过程模型,实现观测变量和关节角度的关联;最后,当得到新的观测变量时,通过训练的高斯过程模型得到机器人的关节角度。经过训练后,UR3机器人成功抓取了物体。