遥感影像弱小目标智能解译算法研究

随着遥感技术的快速发展,光学遥感影像弱小目标智能解译成为遥感信息处理的研究热点之一。遥感影像的地物目标常具有尺度小、种类多、数量大、部分重点小目标移动速度快的特点,易受到复杂背景环境及噪声影响,使得提取遥感影像弱小目标的信息面临着巨大的挑战。早期智能解译算法中的弱小目标分割、检测及跟踪等算法研究,多依赖模板匹配及先验知识,此类算法需耗费大量资源、算力及专家知识成本,存在着计算量大、泛化能力差的问题。近年来,随着深度学习等人工智能技术的快速发展,在海量遥感数据中准确获取弱小目标的信息,通过结合深度学习算法可对弱小目标的特征进行快速提取,以提供高效、准确的解译信息。本文综述了遥感影像弱小目标智能解译算法研究进展,包括基于传统图像处理方法的弱小目标分割、检测和跟踪算法,以及基于深度学习等典型相关算法。通过分析这些方法的优点与局限性,对于提高相关目标的信息获取能力、提升观测的态势感知水平以及未来应用等方面具有重要意义。     

Intrinsic component filtering for fault diagnosis of rotating machinery

Fault diagnosis of rotating machinery has always drawn wide attention. In this paper, Intrinsic Component Filtering (ICF), which achieves population sparsity and lifetime consistency using two constraints: $l_{1/2}$ norm of column features and $l_{3/2}$ -norm of row features, is proposed for the machinery fault diagnosis. ICF can be used as a feature learning algorithm, and the learned features can be fed into the classification to achieve the automatic fault classification. ICF can also be used as a filter training method to extract and separate weak fault components from the noise signals without any prior experience. Simulated and experimental signals of bearing fault are used to validate the performance of ICF. The results confirm that ICF performs superior in three fault diagnosis fields including intelligent fault diagnosis, weak signature detection and compound fault separation.     

Imaginary filtered hindsight experience replay for UAV tracking dynamic targets in large-scale unknown environments

As an advanced combat weapon, Unmanned Aerial Vehicles (UAVs) have been widely used in military wars. In this paper, we formulated the Autonomous Navigation Control (ANC) problem of UAVs as a Markov Decision Process (MDP) and proposed a novel Deep Reinforcement Learning (DRL) method to allow UAVs to perform dynamic target tracking tasks in large-scale unknown environments. To solve the problem of limited training experience, the proposed Imaginary Filtered Hindsight Experience Replay (IFHER) generates successful episodes by reasonably imagining the target trajectory in the failed episode to augment the experiences. The well-designed goal, episode, and quality filtering strategies ensure that only high-quality augmented experiences can be stored, while the sampling filtering strategy of IFHER ensures that these stored augmented experiences can be fully learned according to their high priorities. By training in a complex environment constructed based on the parameters of a real UAV, the proposed IFHER algorithm improves the convergence speed by 28.99% and the convergence result by 11.57% compared to the state-of-the-art Twin Delayed Deep Deterministic Policy Gradient (TD3) algorithm. The testing experiments carried out in environments with different complexities demonstrate the strong robustness and generalization ability of the IFHER agent. Moreover, the flight trajectory of the IFHER agent shows the superiority of the learned policy and the practical application value of the algorithm.     

基于深度强化学习的无人机栖落机动控制策略设计

无人机栖落机动飞行是一种无需跑道的降落方法，能够提升无人机在复杂环境下执行任务的适应能力。针对具有高非线性、多约束特性的无人机栖落机动过程，提出了一种基于模仿深度强化学习的控制策略设计方法。首先，建立了固定翼无人机栖落机动的纵向非线性动力学模型，并设计了无人机栖落机动的强化学习环境。其次，针对栖落机动状态动作空间大的特点，为了提高探索效率，通过模仿专家经验的方法对系统进行预训练。然后，以模仿学习得到的权重为基础，采用近端策略优化方法学习构建无人机栖落机动的神经网络控制器。最后，通过仿真验证了上述控制策略设计方法的有效性。     

基于深度学习的非合作航天器姿态估计

针对空间非合作航天器姿态测量时受光照和地球背景影响大的问题,提出了一种基于卷积神经网络的端到端姿态估计方法.在该方法中,主干网络采用AlexNet与ResNet.首先,移除主干网络末端的全连接层,并列连接3个全连接层,采用三分支网络分别对姿态角进行估计.然后,设计了将分类问题与回归问题相结合的损失函数,通过分类方法将姿态估计限定在某一范围内,再使用回归方法进一步微调姿态.姿态分类损失函数确定姿态角度基准点,姿态回归损失函数对估计角度进行微调.相较于仅采用回归方法进行姿态估计,此方法能够有效减小姿态估计平均绝对误差、标准差与最大误差.实验对比了不同主干网络的测量精度,平均绝对误差在0.376°～0.746°之间,最优标准差为0.474°.     

基于深度学习的航空器异常飞行状态识别

飞行设备快速存取记录仪(Quick Access Recorder,以下简称QAR)保留了原始航班各类重要飞行参数在内的航行信息,使研究分析航空器实时状况和保障飞行质量成为可能。针对QAR数据高维大样本的特点,在如今大数据背景下,除了传统机理建模分析航空器飞行状态外,采用深度学习的方式建立基于数据驱动的航空器飞行状态识别模型,理论与实用意义兼具。通过对真实QAR飞行数据的研究,开发了基于深度稀疏受限玻尔兹曼机的异常飞行状态识别程序。首先利用小波降噪技术对原始飞行数据进行预处理清洗,在一系列典型飞行参数上提取经典时域特征以及小波奇异熵等信息熵特征构成特征集。在此基础上,分别利用经典的线性主元分析技术和深度稀疏玻尔兹曼机对特征集进行有效降维,最后采用四折交叉验证方式,通过高斯过程分类器实现对飞行状态的辨识。实验结果显示,基于深度受限玻尔兹曼机-高斯过程分类的飞行状态识别具有较高分类准确性。     

非对称结构损伤飞机鲁棒容损控制器设计

当飞机发生非对称结构损伤时,飞机的质量、重心位置和气动特性都会发生突变,飞机机体的对称性遭到破坏,致使飞机的横纵向间运动产生强烈的耦合。针对飞机发生非对称结构损伤时导致的飞行控制问题,建立了非对称结构损伤飞机的损伤模型,并基于一种新型鲁棒容损控制策略,采用非线性扩张状态观测器和非线性动态逆相结合的方法,对飞机的姿态控制器进行了设计,兼顾了飞机系统的性能和对损伤的鲁棒性。最后,基于NASA的通用运输机模型,对所设计控制器的控制效果进行了仿真验证。仿真结果表明,设计的姿态控制器有效地抑制了非对称结构损伤给飞机控制系统带来的不确定性和扰动,具有较好的控制性能。     

一种无人机自主避障与目标追踪方法

针对无人机自主避障与目标追踪问题，以深度Q网络(DQN)算法为基础，提出一种多经验池深度Q网络(MP DQN)算法，使无人机避障与追踪的成功率和算法的收敛性得到优化。更进一步，赋予无人机环境感知能力，并在奖励函数中设计了方向奖惩函数，提升了无人机对环境的泛化能力以及算法的整体性能。仿真结果表明，相较于DQN和双重DQN(DDQN)算法，MP DQN算法具有更快的收敛速度、更短的追踪路径和更强的环境适应性。     

基于改进GWO-LightGBM的滚动轴承未知故障诊断

针对滚动轴承未知新故障误判影响轴承安全性和检修效率的问题，提出了一种基于改进灰狼算法（GWO）和轻量级梯度提升机（LightGBM）的故障诊断模型，实现已知/未知故障的高精度判别。为避免单一尺度下特征提取的缺失，对滚动轴承振动信号分别提取时域、频域和小波域特征建立多域特征集。设计了带未知新故障判别机制的GWO-LightGBM模型，并构造含有Halton序列和模拟退火策略的GWO实现了模型参数有效优化。实例试验结果表明，模型对已知和未知类故障平均识别率达99.57%，10次随机试验平均识别率分别比单一分类模型逻辑回归（LR）、最近邻分类器（KNN）和支持向量机（SVM）高21.98%、17.00%、9.27%，验证了模型的有效性和优越性，能高准确率地识别出已知或以前从未出现的新故障。      

Force measurement using strain-gauge balance in shock tunnel based on deep learning

When a force test is conducted in a shock tunnel, vibration of the Force Measurement System (FMS) is excited under the strong flow impact, and it cannot be attenuated rapidly within the extremely short test duration of milliseconds order. The output signal of the force balance is coupled with the aerodynamic force and the inertial vibration. This interference can result in inaccurate force measurements, which can negatively impact the accuracy of the test results. To eliminate inertial vibration interference from the output signal, proposed here is a dynamic calibration modeling method for an FMS based on deep learning. The signal is processed using an intelligent Recurrent Neural Network (RNN) model in the time domain and an intelligent Convolutional Neural Network (CNN) model in the frequency domain. Results processed with the intelligent models show that the inertial vibration characteristics of the FMS can be identified efficiently and its main frequency is about 380 Hz. After processed by the intelligent models, the inertial vibration is mostly eliminated from the output signal. Also, the data processing results are subjected to error analysis. The relative error of each component is about 1%, which verifies that the modeling method based on deep learning has considerable engineering application value in data processing for pulse-type strain-gauge balances. Overall, the proposed dynamic calibration modeling method has the potential to improve the accuracy and reliability of force measurements in shock tunnel tests, which could have significant implications for the field of aerospace engineering.