智能方法在惯性系统误差参数辨识中的应用

总结了目前我国提高惯性系统导航精度的技术途径,阐述了国内外惯性系统误差参数辨识方法的研究现状,介绍了当前滤波算法、智能优化算法和人工神经网络方法在惯性系统导航领域的应用情况以及存在的不足。最后,分析了空间飞行器惯性系统误差参数辨识技术的未来研究方向,即智能优化算法和人工神经网络方法等智能方法将在惯性系统误差参数辨识中发挥越来越重要的作用,通过将误差系数标定问题转换为参数辨识问题,采用智能方法在庞大的解空间内实现对惯性系统误差参数的快速辨识。     

基于小波神经网络PID的永磁同步电机转速控制

提出了基于小波神经网络PID的永磁同步电机(PMSM)转速控制策略。根据系统运行参数的变化,采用三层前馈式人工神经网络,基于梯度下降纠正误差法在线训练实时更新PID参数值。采用小波神经网络和增量式PID共同构成转速环控制器。建立PMSM数学模型,设计PMSM速度环控制器,构建S函数,对控制算法进行仿真试验,验证了该控制算法的先进性。试验结果表明,所提控制策略比传统PID转速控制具有更好的动态性能和抗干扰能力。     

模块化永磁直线游标电机等效磁网络及漏磁分析

在模块化永磁直线游标电机的初始设计及优化设计中,使用有限元方法(FEM)计算漏磁系数时需要耗费大量的建模和计算时间。针对这一问题,建立该种电机的等效磁网络模型,在建模期间,考虑气隙中的边缘效应,并计算永磁体组与定子齿在不同相对位置时的等效磁导,得到该种电机在一个周期内不同相对位置时的漏磁磁导和漏磁系数的数学解析表达式。采用FEM验证了该数学解析表达式的准确性。研究结果为模块化永磁直线游标电机的设计提供了理论依据。     

Bayesian network-based extraction of lunar impact craters from optical images and DEM data

Impact craters are among the most noticeable geomorphological features on the planetary surface and yield significant information about terrain evolution and the history of the solar system. Thus, the recognition of impact craters is an important branch of modern planetary studies. Aiming at addressing problems associated with the insufficient and inaccurate detection of lunar impact craters, a decision fusion method within the Bayesian network (BN) framework is developed in this paper to handle multi-source information from both optical images and associated digital elevation model (DEM) data. First, we implement the edge-based method for efficiently searching crater candidates which are the image patches that can potentially contain impact craters. Secondly, the multi-source representations of an impact crater derived from both optical images and DEM data are proposed and constructed to quantitatively describe the two-dimensional (2D) and three-dimensional (3D) morphology, consisting of Histogram of Oriented Gradient (HOG), Histogram of Multi-scale Slope (HMS) and Histogram of Multi-scale Aspect (HMA). Finally, a BN-based framework integrates the multi-source representations of impact craters, which can provide reductant and complementary information, for distinguishing craters from non-craters. To evaluate the effectiveness and robustness of the proposed method, experiments were conducted on three lunar scenes using both orthoimages from the Lunar Reconnaissance Orbiter (LRO) and DEM data acquired by the Lunar Orbiter Laser Altimeter (LOLA). Experimental results demonstrate that integrating optical images with DEM data significantly decreases the number of false positives compared with using optical images alone, with F₁-score of 84.8% on average. Moreover, compared with other existing fusion methods, our proposed method was quite advantageous especially for the detection of small-scale craters with diameters less than 1000 m.     

基于类脑模型与深度神经网络的目标检测与跟踪技术研究

目标检测与跟踪技术广泛应用于交通、医疗、安保和航天等领域.目前，目标检测与跟踪技术面临目标微弱、背景复杂、目标被遮挡等挑战.同时，随着脑科学研究的不断深入，人们对人脑视觉系统的理解逐渐透彻，利用类脑计算解决复杂背景下高精度目标检测与跟踪问题成为相关领域的重要研究方向.本文结合神经工程导向的类脑模型和计算机工程导向的深度神经网络(Deep Neural Networks, DNNs)，提出多种基于类脑模型与深度神经网络的目标检测与跟踪算法，包括：基于演算侧抑制的目标检测算法，基于结构 对比度(Structure Contrast, SC)视觉注意模型的弱小目标检测算法和基于记忆机制与分层卷积特征的目标跟踪算法.实验结果表明，将类脑模型和深度神经网络应用于目标检测和跟踪领域，有利于实现复杂条件下的高精度目标检测和鲁棒性目标跟踪.     

Rotating machinery fault diagnosis based on convolutional neural network and infrared thermal imaging

Rotating machinery is widely applied in industrial applications. Fault diagnosis of rotating machinery is vital in manufacturing system, which can prevent catastrophic failure and reduce financial losses. Recently, Deep Learning (DL)-based fault diagnosis method becomes a hot topic. Convolutional Neural Network (CNN) is an effective DL method to extract the features of raw data automatically. This paper develops a fault diagnosis method using CNN for InfRared Thermal (IRT) image. First, IRT technique is utilized to capture the IRT images of rotating machinery. Second, the CNN is applied to extract fault features from the IRT images. In the end, the obtained features are fed into the Softmax Regression (SR) classifier for fault pattern identification. The effectiveness of the proposed method is validated using two different experimental data. Results show that the proposed method has a superior performance in identification various faults on rotor and bearings comparing with other deep learning models and traditional vibration-based method.     

月球表层采样样品智能确认方法

表层采样是月球采样探测的重要方式，样品智能确认有助于提升工作效率与复杂问题处理能力。结合月球表层采样铲挖工作过程，分析了铲挖过程中臂载相机图像的特点，模仿有人参与识别过程，提出了层次解耦的月球样品智能识别流程，利用深度学习方法构建了一类深度卷积识别网络，完整地描述了图像、特征、标记在网络中的正反传递关系，并在月球表层采样地面试验中进行了验证，结果表明该方法对不同光照、不同背景、不同过程、不同形态的样品，具有较好的泛化识别能力，误识别率优于8.1%，平均单幅识别时间约0.7 s。     

基于NB-IoT技术和GA-BP神经网络的车位预测系统

围绕有效整合城市停车资源,提高现有车位存量利用率的需求,构建了一种基于NB-IoT技术的车位预测系统。该系统采用NB-IoT技术进行信息采集与传输实现车位信息的共享;考虑到车位状态信息实时变化的特性,用历史车位占用数据来建立车位预测模型,推测出未来短时内车位变化趋势。为了提高车位预测的精度,采用遗传算法(Genetic algorithm,GA)优化反向传播(Back propagtion,BP)神经网络建立GA-BP神经网络车位预测模型。以某地下停车场历史数据为例进行仿真实验,研究结果表明:车位预测模型预测值与实际值相近且趋势保持一致,能够有效准确的预测车位状态变化,具有较高的精度。     

An innovative approach for integrated airline network and aircraft family optimization

The determination of optimal aerial transport networks and their associated flight frequencies is crucial for the strategic planning of airlines, as well as for carrying out market research, to establish target markets, and for aircraft and crew rostering. In addition, optimum airplane types for the selected networks are crucial to improve revenue and to provide reduced operating costs. The present study proposes an innovative approach to determine the optimal aerial transport network simultaneously with the determination of the optimum fleet for that network, composed of three types of airplanes (network and vehicle integrated design). The network profit is maximized. The passenger’s demands between the airports are determined via a gravitational model. An embedded linear programming solution is responsible for obtaining potential optimal network configurations. The optimum fleet combination is determined from a database of candidate aircraft designs via genetic algorithm. A truly realistic airplane representation is made possible thanks to accurate surrogate models for engine and aerodynamics is adopted. An accurate engine deck encompassing a compression map and an innovative engine weight calculation besides an aerodynamical artificial neural network module enable a high degree of accuracy for the mission analysis. The proposed methodology is applied to obtain the optimum network comprised of twenty main Brazilian airports and corresponding fleet.     

基于函数链神经网络的深度分类器

目前的宽度学习系统（Broad learning system，BLS）通过所建立的一系列映射节点和增强节点来形成联合节点。因为联合节点与输出层的线性连接，网络权值可以用求解伪逆的方法快速求得，避免了耗时的训练过程，从而成为快速而高效的学习方法。然而在追求高精度结果的过程中，BLS对于增强节点数量的需求过于巨大，容易造成过拟合问题。为此，本文提出了基于函数链神经网络（Functional-link neural network，FLNN）的深度分类器（FLNN based deep classifier，FLNNDC），旨在提供一种更加简单却又不失精度的BLS变体结构。FLNNDC将几个轻量级的BLS子系统堆积成栈式结构，每一个轻量级的BLS子系统随机选择一部分映射节点生成增强节点，而不是全部映射节点。和原宽度结构相比，在几个主流数据集上的实验结果表明本文所提出的FLNNDC分类器具有网络结构更小且学习速度更快的优势。