一种星-箭连接动态界面力的深度学习反演方法

针对于星-箭连接动态界面力无法通过力传感器直接测量,且典型时域动载反演方法难以准确计算界面力的时域变化等难点,提出了基于长短时记忆(LSTM)神经网络的星-箭界面力深度学习反演方法。首先通过卫星地面测试试验得到数据依据,以卫星主体结构的加速度测量数据为输入层,以星-箭界面力测量数据为输出层,利用LSTM神经网络建立输入和输出间的反演映射关系模型,实现卫星在发射过程中较高精度的界面力反演。进而,设计并开展了某典型卫星结构的正弦扫频和随机振动实验,测试LSTM界面力反演方法的可行性。结果分析可知,所提出的基于LSTM深度学习反演方法能够精确地获得动态界面力时程数据,两项性能指标均优于目前典型的载荷反演方法。     

航空活塞式发动机空燃比实时控制算法

采用比例-积分-微分神经网络(PIDNN)的控制算法,集合了传统PID控制及神经网络各自的优点,控制发动机在不同工况下的空燃比,实现发动机在不同工况间切换时,能够快速地控制空燃比至目标值.在AMESim软件中建立发动机模型,在MATLAB软件中建立PIDNN控制算法,进行模型在环仿真,仿真结果表明:在不同海拔高度下,PIDNN控制算法都能够准确地把空燃比控制在目标值,当发动机在不同工况间切换时,PIDNN能够在0.5s内把发动机空燃比控制至目标值,并且保证过量空气系数超调量在0.2之内,改善了发动机的动力性、经济性,提高了发动机的响应能力.     

Optimization of beamforming and path planning for UAV-assisted wireless relay networks

Recently, unmanned aerial vehicles （UAVs） acting as relay platforms have attracted considerable attention due to the advantages of extending coverage and improving connectivity for long-range communications. Specifically, in the scenario where the access point （AP） is mobile, a UAV needs to find an efficient path to guarantee the connectivity of the relay link. Motivated by this fact, this paper proposes an optimal design for beamforming （BF） and UAV path planning. First of all, we study a dual-hop amplify-and-forward （AF） wireless relay network, in which a UAV is used as relay between a mobile AP and a fixed base station （BS）. In the network, both of the AP and the BS are equipped with multiple antennas, whereas the UAV has a single antenna. Then, we obtain the output signal~to-noise ratio （SNR） of the dual-hop relay network. Based on the criterion of maximizing the output SNR, we develop an optimal design to obtain the solution of the optimal BF weight vector and the UAV heading angle. Next, we derive the closed-form outage probability （OP） expression to investigate the performance of the dual-hop relay network conveniently. Finally, computer simulations show that the proposed approach can obtain nearly optimal flying path and OP performance, indicating the effectiveness of the proposed algorithm. Furthermore, we find that increasing the antenna number at the BS or the maximal heading angle can significantly improve the performance of the considered relay network.     

基于模块度的复杂网络社团结构聚类新算法

针对传统的分裂聚类算法删除连边会影响节点划分的问题,结合K-means算法的思想并加以改进,提出了一种以邻居节点为聚类备选集,所有社团中心节点同时聚类的同步聚类算法。该算法根据节点中心度和最短路变化率确定社团中心节点集,然后以中心节点为社团中心,以邻居节点为聚类备选集合进行聚类,完成社团的划分。将算法应用到Zachary网络中并与GN算法、Top Leader算法进行比较,仿真结果表明该算法对网络有较好的划分。     

基于BP网络的机组工作量评估方法研究

为研究机组工作量的评估问题,搭建了模拟飞行实验平台,设定了7种不同负荷的飞行任务。模拟飞行中,对被试的生理指标进行测量,并采集其主观评价值。采用BP网络进行数学建模,将生理指标测量值作为输入、NASA-TLX表法的评价值作为输出,利用输入、输出模式对对网络进行训练,并对该方法进行验证。结果表明,基于BP网络的机组工作量评估方法,较传统方法更为稳定、精确,且大大降低了被试数量。提高训练模式对的数量、简化生理指标的测量过程,并保证测量精度是该方法成功的关键。     

有线电视HFC网络与光纤链路设计

本文论述了双向传输有线电视ＨＦＣ网络结构并比较了其优缺点，文中还就工程应用的实例讨论了光纤链路的设计问题。     

基于神经网络的智能刀具状态检测系统

可靠的在线刀具磨损状态检测是柔性制造系统、计算机集成制造系统以及自动化机床必不可少的一个环节。文中论述了用反传神经网络与一类模糊神经网络分析处理由力传感器和声发射传感器所测得的刀具状态信号，识别出刀具的磨损情况，从而进一步实现刀具磨损状态的在线检测，控制自动机床及时更换刀具。本研究对四种规格的钻头的磨损情况进行了全程检测，并比较分析了反传神经网络与模糊神经网络对这一问题的有效性。实验结果表明，这两种方法对处理刀具磨损状态检测均有显著的效果与很高的准确性。用一类模糊神经网络处理多传感器信息是实现刀具状态在线检测的一个极为有效的方法。     

基于Hamming神经网络聚类分析的进化策略

本文提出了一种基于Ｈａｍｍｉｎｇ神经网络聚类分析的进化策略，模糊自适应Ｈａｍｍｉｎｇ神经网络各类族的权重矢量纪录被进化搜索过的区域，并相应妄下该区域内最优个体和它的适应度，因此通过Ｈａｍｍｉｎｇ神经网络对进化个体的聚类分析，进化策略具有搜索记忆性，可以充分保证下一代遗传群体中个体遗传基因的丰富性，从而避免早熟现象的发生，这种进化策略还可以避免在被搜索过的区域内的无用搜索，进而加快进化策略的收敛速度     

Design and Application of Discrete Sliding Mode Control with RBF Network-based Switching Law

This article proposes a novel approach combining exponential-reaching-law-based equivalent control law with radial basis function (RBF) network-based switching law to strengthen the sliding mode control (SMC) tracking capacity for systems with uncertainties and disturbances. First, SMC discrete equivalent control law is designed on the basis of the nominal model of the system and the adaptive exponential reaching law, and subsequently, stability of the algorithm is analyzed. Second, RBF network is used to form the switching law in a direct and online manner with sliding-mode-related inputs and by approximating evaluation function; and the method to adjust its parameters is devised. Finally, comparable experiments are carried out to verify the application of the proposed approach to an inner-axis driven by a direct current (DC) torque motor through extra-low speed servo for a high precision flight simulator, and the axis works under deteriorating conditions such as periodically fluctuating torques of motor, nonlinear friction, and time-varying model parameters. The results show that the combined SMC can effectively improve the servo performance, for instance, to a stable 0.000 08 (°)/s speed response, the tracking error would be within 0.000 08° in 98% of operating times. Moreover, the hybrid nature of the approach imparts the RBF network the features of removing offline training and ease to set initial parameters.     

Using the radial basis function neural network to predict ionospheric critical frequency of F2 layer over Wuhan

Neural networks (NNs) have been applied to ionospheric predictions recently. This paper uses radial basis function neural network (RBF-NN) to forecast hourly values of the ionospheric F₂ layer critical frequency(f_oF₂), over Wuhan (30.5N, 114.3E), China. The false nearest neighbor method is used to determine the embedding dimension, and the principal component analysis (PCA) is used to reduce noise and dimension. The whole study is based on a sample of about 26,000 observations of f_oF₂ with 1-h time resolution, derived during the period from January 1981 to December 1983. The performance of RBF-NN is estimated by calculating the normalized root-mean-squared (NRMSE) error, and its results show that short-term predictions of f_oF₂ are improved.