基于LMS和SDP的发动机异响诊断方法研究

为有效提取发动机声信号特征,以诊断发动机的异响,提出了一种以最小均方算法和对称点图形算法相结合的发动机异响诊断方法。采用最小均方算法去除信号中的噪声,还原发动机声信号,而利用SDP图形技术将信号转换为极坐标图形,得以判断发动机是否产生异响。通过仿真与试验,验证了该方法的有效性。     

基于三阶段最小二乘法探究诱增交通量

在诱增交通量的预测中,中国现有统计数据在精度和广度上的局限性,容易造成计算结果存在遗漏变量偏误和测量误差偏误;同时变量之间的相关性容易导致计算结果存在联立性问题。为克服这些问题,采用工具变量法中的三阶段最小二乘法探讨道路供给与交通需求之间的关系。基于国家统计数据库数据,选择车辆出行距离、民用汽车拥有量和交通拥堵水平三个内生变量构建联立方程模型,采用三阶段最小二乘法对联立方程进行估计,并给出短期、长期弹性系数的求解方法。结果表明,道路建设会导致车辆出行距离增加,不能解决中国城市交通拥堵问题,而大力发展公共交通可以降低交通拥堵水平。     

基于遗传算法的近红外光谱建模样品集优化研究

探讨遗传算法优化方法在南丰蜜橘内部品质可溶性固形物的建模集样品选择中的应用,根据优化结果建立了南丰蜜橘可溶性固形物的快速无损检测数学模型。研究选择的波长范围为350—1800nm,应用遗传算法优化建模集样品,优化后建模集样品数量由89个减少到36个,累积变异系数达到99．99％,交互验证均方根误差达到最小。研究结果表明：优化后的建模样品数量大大减少,且保证了南丰蜜橘可溶性固形物的快速无损检测数学模型的稳定性。     

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.     

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.     

基于GIS公交查询系统的设计与实现

本文充分考虑了乘客出行心理后,设计了以换乘次数最少和出行耗时最少作为约束目标的公交出行最优路径算法。利用动态分段技术建立了公交信息数据库,采用Visualc#．NET＋MapX5．0集成开发的方式开发了公交信息查询系统,实现了输入查询或直接对地图操作来获得出行最优路线和换乘方案。系统以济南市公交网络为基础进行了测试,测试结果良好,为居民的出行提供了一个方便、快捷的公交路线查询平台。     

用结构化非线性最小范数法识别包装系统模态参数

考虑到包装系统的复杂性,可将包装件建模为多模态系统.对结构化非线性最小范数法进行改进,推导出了识别系统自由响应的零点和留数的迭代法,该方法采用以Prony方法识别出的系统的零点和留数为迭代起点,模拟结果表明：该方法与Prony方法相比具有更好的精确性,为准确识别包装系统各模态的参数打下基础.     

基于最小二乘法的测力环线性回归分析与检验

基于最小二乘法的线性回归分析法是解决测力环线性拟合方程的分析方案。理论分析证实,基于最小二乘法的测力环线性回归分析法建立的回归方程回归直线误差（标准差）最小,是测力环回归分析的最佳方法,可为公路工程试验检测提供较高精度的数据处理途径,其试验数据处理与Excel相结合可大大提高工作效率,并得到直观的曲线拟合界面。     

非线性最小二乘参数平差的非线性规划算法研究

讨论了非线性最小二乘参数平差可行的5种非线性规划算法－牛顿法、最速下降法、离散牛顿法、拟牛顿法和SQPM算法,通过分析、比较和实算证实SQPM算法是求解非线性最小二乘参数平差问题的最为有力的工具,且使SQPM算法成为无需精确计算参数概略值的非线性最小二乘参数平差法。     

A DYNAMICAL SYSTEM ALGORITHM FOR SOLVING A LEAST SQUARES PROBLEM WITH ORTHOGONALITY CONSTRAINTS

Introduction　　 During the past decade,many people havebeen interested in solving problems in optimiza-tion,matrix algebra,signal processing and manyotherfields by dynamical system(neural networks)algorithms[1～ 3 ] .The significance benefit is thatthis kind of algorithms can be realized by someproperly designed hardware (electronic implemen-tation) and thus desired solutions can often be ob-tained in a fast speed,real time algorithms forproblems considered are therefore provided.In thispaper…