Least Squares Support Vector Machine Based Real-Time Fault Diagnosis Model for Gas Path Parameters of Aero Engines

Least squares support vector machine (LS-SVM) is applied in gas path fault diagnosis for aero engines.Firstly,the deviation data of engine cruise are analyzed.Then,model selection is conducted using pattern search method.Finally,by decoding aircraft communication addressing and reporting system (ACARS) report,a real-time cruise data set is acquired,and the diagnosis model is adopted to process data.In contrast to the radial basis function (RBF) neutral network,LS-SVM is more suitable for real-time diagnosis of gas turbine engine.     

悬索桥施工监控计算分析

悬索桥的施工包括索塔施工、锚旋施工、猫道架设、索鞍安装、主缆架设及紧缆、索夹吊索安装、加劲梁安装、桥面系及防护工程等内容,相当复杂。对悬索桥的施工过程进行监控．对各工序下的控制参数进行跟踪监测、调整、控制,确保施工过程安全和成桥后结构受力和变形尽量与设计状态一致,成为非常重要的问题。悬索桥跨径越大,这个问题越显得重要。     

A study on the degree of barrier coverage in wireless sensor networks

Recently, the barrier coverage was proposed and received much attention in wireless sensor network (WSN), and the degree of the barrier coverage, one of the critical parameters of WSN, must be re-studied due to the difference between the barrier coverage and blanket coverage. In this paper, we propose two algorithms, namely,local tree based no-way and back (LTNWB) algorithm and sensor minimum cut sets (SMCS) algorithm, for the opened and closed belt regions to determine the degree of the barrier coverage of WSN. Our main objective is to minimize the complexity of these algorithms. For the opened belt region, both algorithms work well, and for the closed belt region, they will still come into existence while some restricted conditions are taken into consideration.Finally, the simulation results demonstrate the feasibility of the proposed algorithms.     

Constrained submap algorithm for simultaneous localization and mapping

When solving the problem of simultaneous localization and mapping (SLAM), a standard extended Kalman filter (EKF) is subject to linearization errors and causes optimistic estimation. This paper proposes a submap algorithm, which builds a weighted least squares (WLS) constraint between two adjacent submaps according to the different estimations of the common features and the relationship between the vehicle poses in the corresponding submaps. By establishing the constraint equation after loop closing, re-linearization is implemented and each submap’s reference frame tends to its equilibrium position quickly. Experimental results demonstrate that the algorithm could get a globally consistent map and linearization errors are limited in local regions.     

隧道竣工后中心线形确定的一种新方法

介绍并比较了隧道竣工后中心线形确定的最小二乘直接拟合椭圆法、最小平方中值拟合椭圆法,在此基础上提出了一种新方法。即结合两种椭圆拟合方法的优缺点进行组合,并通过样本分位值法先剔除数据中的粗差再进行拟合,增强了拟合结果的稳健性,并以某公路隧道竣工后实测数据进行了验证。     

基于最小二乘支持向量机的公路软基沉降预测

通过影响因素分析,确定了软土层厚度、软土层压缩模量、地表硬层厚度、地表压缩模量、路堤高度、路堤顶宽、路基填筑时间和填筑竣工时沉降量等参数对公路软基沉降有影响.对公路软基的观测数据进行分析和取样,输入样本为各参数,输出样本为路堤中线下地表沉降值,利用最小二乘支持向量机的非线性映射和泛化能力,通过训练,建立了公路软基沉降预测模型.研究表明,所建立的模型对公路软基沉降进行预测具有较高的精度,同时具有很好的泛化性能.     

西班牙一座高架桥的设计

在西班牙的普奇雷奇小城,一座跨越略夫雷加特（Llobregat）河的高架桥于2007年10月竣工并通车。桥梁线形基本上设计为直线,在贝尔加侧桥台附近设1处曲线,最小曲线半径为600m。     

图最小覆盖算法在城市电子眼布点中的应用

电子眼是智能交通系统的重要组成部分,电子眼在我国拥有一个广阔的发展前景.将城市电子眼布点的经济合理性问题转化为求图的最小顶点覆盖问题,以某城市高教园区道路网为实例,运用图的最小覆盖启发式算法进行求解,得出了结论.     

基于在线LS-SVM的α阶逆控制

提出基于最小二乘支持向量机在线算法的α阶逆控制方法．引入系统控制误差不敏感函数,在控制误差大于不敏感函数时,利用增量一剪枝学习算法,对已建立的离线逆控制器实施在线学习,以增强控制系统的鲁棒性．仿真结果表明：在系统没有受到噪声干扰时,在线逆控制器可以很好地使被控对象跟踪参考输入信号;在系统受到噪声干扰时,在线逆控制器比离线逆控制器具有更强的鲁棒性．     

城市快速路路段交通流状态评估方法

交通流状态分类对于选择交通控制和诱导策略有非常重要的作用,不同的快速路路段设定的交通流参数临界值及变化特性会有所不同．本文考虑到交通流参数对交通流状态判别的影响程度,给出了一种基于加权欧氏距离的相似性度量方法,并确定了交通流状态判别的关键参数．根据整个路段的交通流数据,通过聚类分析构造最小距离分类器,把个别路段的交通流数据作为样本数据．进行了对个别路段的状态评估．实证分析结果表明：在交通流状态判别过程中,密度是最关键的参数：基于最小距离分类的个别路段的状态评估结果与实际情况非常类似,这将为交通控制和管理提供决策依据．