基于神经网络的类乘波体飞行器FADS算法研究

大气数据是飞行器飞行的重要参数,大气数据系统是必备的机载航电系统。嵌入式大气数据系统（FADS）是新一代大气数据系统,可用于类乘波体飞行器。飞行器外形特殊,大飞行包线内FADS压力场模型复杂,解算算法尚不完备。针对飞行器的特点,利用三维几何建模和计算流体动力学（CFD）计算的方法,分析FADS压力场模型特性,设计并验证了基于神经网络的类乘波体飞行器FADS算法,结果表明,算法对马赫数、攻角和侧滑角大气参数的解算可行有效。     

PSO-RBF神经网络在舵机系统故障诊断中的应用

文章建立了基于RBF神经网络的故障观测器模型,提出了一种将粒子群优化算法(PSO)与正则化正交最小二乘法(ROLS)相结合的2级RBF学习方法,并将该RBF网络观测器应用于导弹舵机系统的故障诊断.实验结果表明,基于该RBF神经网络的故障观测器能够有效地实现导弹舵机系统的故障检测.     

贝叶斯网络在飞控系统可靠性评估中的应用

把一种基于贝叶斯网络的故障树分析法应用于飞控系统俯仰控制功能的可靠性评估中,突破传统故障树分析法的局限性——各部件独立、状态为二值,不但可以计算系统的可靠性指标,而且可以定量给出某个事件或某几个事件在系统可靠性中所占的地位,找出系统的薄弱环节。     

基于BP神经网络的机载数字高程模型压缩

现有的数字高程模型压缩方法大多从编码方式上进行优化,而很少利用其数据的自相关性。为此,提出了一种采用L-M训练算法的单隐层BP神经网络实现机载数字高程模型压缩的新方法,并给出了实现压缩的详细过程。论述了采用单隐层网络的理由,并根据机载要求的相对误差精度去选择最少的隐层节点数。通过选取ASTERGDEM30米分辨率的高精...     

基于贯序正则极端学习机的时间序列预测及其应用

为实现对液压泵特征参数的在线预测,提出一种贯序正则极端学习机(SRELM),并研究了基于SRELM的预测方法.SRELM根据结构风险最小化原理实现网络训练,其网络权值可随新样本的逐次加入而递推求解,具有泛化能力强与训练速度快的优点,因此适于特征参数的在线预测.基于SRELM的预测方法利用特征参数训练SRELM模型,以逐...     

适于长传播时延无线网络的快速预约按需发送MAC协议

为解决无线网络中长传播时延所带来的信道资源利用率低的问题,提出一种基于快速预约按需发送(FRODT)的媒质接入控制(MAC)协议.该协议利用中心控制节点(CCN),在两个信道上安排各节点的分组预约和发送,保证了各节点可以在一帧中无碰撞地发送一个或多个业务分组,并且各节点通过一次握手预约即可完成整个通信会晤的业务分组发送...     

New Neural Network Response Surface Methods for Reliability Analysis

This article presents two new kinds of artificial neural network (ANN) response surface methods (RSMs): the ANN RSM based on early stopping technique (ANNRSM-1), and the ANN RSM based on regularization theory (ANNRSM-2). The following improvements are made to the conventional ANN RSM (ANNRSM-0): 1) by monitoring the validation error during the training process, ANNRSM-1 determines the early stopping point and the training stopping point, and the weight vector at the early stopping point, which corresponds to the ANN model with the optimal generalization, is finally returned as the training result; 2) according to the regularization theory, ANNRSM-2 modifies the conventional training performance function by adding to it the sum of squares of the network weights, so the network weights are forced to have smaller values while the training error decreases. Tests show that the performance of ANN RSM becomes much better due to the above-mentioned improvements: first, ANNRSM-1 and ANNRSM-2 approximate to the limit state function (LSF) more accurately than ANNRSM-0; second, the estimated failure probabilities given by ANNRSM-1 and ANNRSM-2 have smaller errors than that obtained by ANNRSM-0; third, compared with ANNRSM-0, ANNRSM-1 and ANNRSM-2 require much fewer data samples to achieve stable failure probability results.     

Cooperative Routing for Maximizing Network Performance of Wireless Networks

To greatly increase spectral efficiency and improve network performance in wireless networks,a novel cooperative routing algorithm,namely maximum throughput cooperative routing(MTCR) algorithm,is proposed.According to cooperative link model,throughput analysis is presented to evaluate performance improvement in the process of exploiting cooperative commu-nication from physical layer to higher layer.Taking the throughput improvement as performance metric,a cooperative relay se-lection scheme is developed.Finally,based on the route constructed by adaptive forwarding cluster routing(AFCR) algorithm,each node on the route selects the optimum cooperative node from all the potential cooperative nodes to construct the coopera-tive link with maximum throughput so that cooperative route with maximum network throughput from source to destination can be set up.Simulation results show that compared with the noncooperative routing algorithm and minimum power selection de-code-and-forward(MPSDF) routing algorithm,the proposed algorithm can obviously improve network throughput in the pres-ence of low transmission power,large number of nodes and high spectral efficiency.     

基于BP神经网络的金属橡胶本构关系的预估方法

采用BP(back propagation)神经网络算法对金属橡胶的本构关系系数进行学习训练,对BP神经网络做了比较详细的介绍,讨论了如何运用神经网络去预估金属橡胶的非线性本构关系系数,选择了BP神经网络参量,通过对金属橡胶的静态压缩实验数据进行参数识别,获得仅材料密度变化、材料密度和形状因子两种因素同时变化两种情况的...     

涡轴发动机自适应混合诊断模型高斯加权聚类方法

针对整个飞行包线内涡轴发动机健康参数估计问题,提出基于高斯加权聚类的机载自适应混合模型建立方法.机载自适应混合模型由卡尔曼滤波器和神经网络组成,由于飞行数据样本庞大,采用高斯加权模型对涡轴发动机飞行数据进行实时聚类,利用聚类数据更新神经网络权重,并实现自适应混合模型工作范围的自动扩展.仿真结果表明了该方法的有效性,采用...