近红外光谱分析中建模样品优选方法的研究

结合牛奶成分近红外光谱测量系统的实例,在已定的浓度范围内针对牛奶中脂肪、蛋白质、乳糖三成分采用正交设计法优选参与建模的样品.研究中首次利用正交表的\     

A new method for solving Dyadic Green’s Function of electromagnetic field

A new method for solving electromagnetic field boundary value problem is given. By using this method, the boundary value problem of the vector wave equation can be transformed into the independent boundary value problem of scalar wave equations and the two additional vector differential operations. All the dyadic Green’s functions got by eigenfunction expansion of the dyadic Green’s function can be got by this method easily and some of the dyadic Green’s functions for complex systems which are very difficult to get by the ordinary method have been got by this new method. The dyadic Green’s function for a dielectric loaded cavity is one of the given examples. This project is supported by the National science Fundation of China     

ZWK-100注塑机微机控制系统

ZWK-100注塑机微机控制系统,是新近研制开发的具有汉字和曲线显示功能,适用于1万克及其以上大型注塑机的微机电气控制系统.本文介绍其工作过程,硬软件结构及其性能等.     

K插值单纯形法核极限学习机的研究

针对核极限学习机高斯核函数参数选优难,影响学习机训练收敛速度和分类精度的问题,该文提出一种K插值单纯形法的核极限学习机算法。把核极限学习机的训练看作一个无约束优化问题,在训练迭代过程中,用Nelder-Mead单纯形法搜索高斯核函数的最优核参数,提高所提算法的分类精度。引入K插值为Nelder-Mead单纯形法提供合适的初值,减少单纯形法的迭代次数,提高了新算法的训练收敛效率。通过在UCI数据集上的仿真实验并与其它算法比较,新算法具有更快的收敛速度和更高的分类精度。     

基于循环匹配追踪的稀疏重构时延估计算法

在单样本(SMV)、低信噪比条件下,稀疏重构方法可提升时延估计精度,但现有的重构算法在支撑集元素的选择中存在错选和漏选的情况,从而导致估计精度受限。针对上述问题,该文提出一种基于循环匹配追踪(LMP)的稀疏重构时延估计算法。该方法引入了“循环删除,匹配添加”的思想,有效提升了直达径的估计精度。算法首先建立信道冲激响应稀疏表示模型;然后在获得初始支撑集的前提下,先循环删除支撑集内的元素,再从支撑集补集中依据与当前残差内积值最大来匹配添加新元素,直至残差内积基本不变;最后利用时延值与稀疏支撑集的关系得到了时延的估计值。仿真结果表明,所提算法相比于传统稀疏重构时延估计算法具有更高的估计精度。同时基于USRP平台,利用实际信号对所提算法进行了有效性验证。

     

Spatial hybrid/parallel force control of a hexapod machine tool using structure-integrated force sensors and a commercial numerical control

Structure-integrated force measurement in hexapod structures or kinematics offers great potential for spatial process force control in six degrees of freedom. Although force control has been studied for many years, research questions remain unanswered, especially when regarding parallel kinematic machine tools with numerical control and integrated sensors. This contribution summarizes the technology of structure-integrated force sensing in hexapod machine tools and develops two approaches to use the measured signals for direct hybrid/parallel force control. For different use-cases, such as teach-in or synchronous force/position control with variable task frame, different approaches of set-point specification and injection of manipulated values are studied from a practical point of view. As a result of the work, the feasibility of the force control with structure-integrated sensors on a commercial CNC can be confirmed through appropriate experiments. Furthermore, the realized G-Code integration represents a practical solution for programming force-controlled machine tools in an easy and concise way from the NC programme.     

引入模块化概念的贴装设备

向模块化组装生产线方向发展正获得愈来愈多人们的关注。一条由多种“高速模块”所组成的生产线具有许多优点,将对现有的装配厂商具有很大的诱惑力。由高速柔性化贴装设备所组成的组装生产线可以超越传统的芯片射手和微细间距贴装设备。     

局部子空间自适应核函数网络

针对目前单一整体核函数网络相对于原始空间特征局部分布缺乏自适应性以及网络规模巨大的不足,本文提出局部子空间自适应核函数网络解决思路。首先将原始空间的高维特征分成一系列低维子空间;然后针对不同子空间构造不同的核函数和核参数局部网络;最后综合所有子空间形成综合核函数网络。同时利用支持向量分布几何意义,选择边界向量代替原始训练样本,大大减少网络的复杂度。由于不同输入子空间构造的核函数以及网络规模相对于样本分布具有一定的自适应性,所以该方法相对于经典全局核函数网络可以得到更好的综合性能。对比实验结果表明本文提出的方法能够改进高维模式识别的性能,是一种值得实际应用推广的方法。     

支持向量机训练算法及其应用

支持向量机是在统计学习理论基础上提出的一种新的机器学习方法。由于其出．色尊学习性能，该技术已成为机器学习界的研究热点，并成功地应用在模式识别、时间序列预测、苛线性系统辨识、控制及其它方面。本文简要介绍了支持向量机训练算法及其应用，并且讨论了未来的发展方向。     

Structural image retrieval using automatic image annotation and region based inverted file

Image retrieval has lagged far behind text retrieval despite more than two decades of intensive research effort. Most of the research on image retrieval in the last two decades are on content based image retrieval or image retrieval based on low level features. Recent research in this area focuses on semantic image retrieval using automatic image annotation. Most semantic image retrieval techniques in literature, however, treat an image as a bag of features/words while ignore the structural or spatial information in the image. In this paper, we propose a structural image retrieval method based on automatic image annotation and region based inverted file. In the proposed system, regions in an image are treated the same way as keywords in a structural text document, semantic concepts are learnt from image data to label image regions as keywords and weight is assigned to each keyword according to spatial position and relationship. As the result, images are indexed and retrieved in the same way as structural document retrieval. Specifically, images are broken down to regions which are represented using colour, texture and shape features. Region features are then quantized to create visual dictionaries which are similar to monolingual dictionaries like English or Chinese dictionaries. In the next step, a semantic dictionary similar to a bilingual dictionary like the English–Chinese dictionary is learnt to mapping image regions to semantic concepts. Finally, images are then indexed and retrieved using a novel region based inverted file data structure. Results show the proposed method has significant advantage over the widely used Bayesian annotation models.