大型过程优化问题降维分解的研究

在过去10年里,SQP算法由于研究了一些降维分解策略,如BLW分解、LEW分解和RND分解,在求解大型过程优化问题中获得了成功的应用.本文提出一种新的降维分解(LMD)方法,它包括LEW分解和RND分解为特例,并在LMD基础上应用数值相关理论处理可能出现的矩阵病态问题,给出一个求解大型问题的快速稳健的算法.

基于后件模糊集中心的Mamdani模糊系统的降维分解

模糊系统是通过模糊规则来处理不确定信息的一种重要工具,而Mamdani模糊系统则是最简单的一类高维系统模型.文章首先从理论上指出Mamdani模糊系统的传统分解存在错误,并分别针对二维和三维Mamdani模糊系统的实际分解公式进行了分析.其次,基于后件(输出)模糊集中心指标重新获得了n维Mamdani模糊系统的降维分解公式.最后,通过实例分析说明该分解公式不仅可以降低高维Mamdani模糊系统的空间维数,而且也可减少系统内部的模糊规则总数.

基于傅里叶级数频率分解的汇流参数确定方法初探

采用傅里叶级数频率分解特性将总径流包含的3种不同频率水源分离,构建了不同水源间参数独立且和频率相关的目标函数,通过理想模型的实例分析验证了该方法的可行性。结果表明,该方法信息量增加,实现了汇流参数分层分频率定,解决了汇流参数率定的局部优值、率定结果不稳定和不合理问题。

CRM分解图的压缩及其化简

CRM分解图可以用来指导超大规模集成电路的设计和化简.本文在分析应用CRM分解图进行逻辑函数或-符合式化简的基础上提出了逻辑函数的降维CRM分解图,给出了降维CRM分解图的定义和图形化简方法.实例表明,该图形方法有直观、简单等特点,它能给出逻辑函数的最简或-符合式,使电路实现比传统设计更简单、更有效.

无梯度多参数自动历史拟合方法

通过历史拟合以降低油藏地质参数的不确定性,提出一种稳定高效的无梯度多参数最优化调参技术,根据贝叶斯统计理论建立历史拟合最小化数学模型,并利用奇异值分解算法进行降维分解,然后采用基于方向导数的无梯度算法对该最优化问题进行求解。该方法同时实现了渗透率、孔隙度、相对渗透率、原油黏度及水体参数的拟合,进一步降低了反问题的不确定性。与人工历史拟合结果相比,基于降维方法的自动历史拟合结果表现出高度的一致性,节省了大量的人力与机时,证明了该方法的有效性与正确性。

二次曲线拟合算法的统计性能分析与改进

传统的二次曲线拟合使用标准特征值分析算法。通过统计分析技术 ,可知该技术在拟合数字二次曲线时 ,存在估计偏差大、均方误差大的缺点。其产生原因是数据噪声的有色性和自相关函数矩阵的条件数过大 ,因此白化数据噪声和正则化变换是提高曲线拟合的有效措施。这从理论上有力地支持了Hartley提出的正则化算法。通过理论分析和计算机仿真实验 ,表明了降维EVD技术固有地同时具备噪声预白化功能和数据正则化功能 ,因此它能给出均方误差相当小的无偏估计。由于它无须进行预白化变换或正则化变换 ,并把最优化过程的维数从 6降为 2 ,所以它还具有计算快速、实现简单方便的优点。

Screening and Isolation of Highly Efficient Cellulose-degrading Microorganisms and Construction of Complex Microbial System

This study almed to screen a highIy efficient ceI uIose-degrading compIex microbial system from soiI and rotten straw and then study its appIication to natural ceI uIose. The isoIated stralns were preIiminariIy screened with Congo red stalning and the ceI uIases activities were determined with DNS method. The non-antagonis-tic highIy efficient ceI uIos-degrading stralns were seIected and cuItured combinedIy for deveIoping a ceI uIose-degrading compIex microbial system. The resuIts showed that the CMC enzyme activity of the mixed cuIture of the three fungi stralns was higher than those of the cuItures of the three singIe stralns. The morphoIogical and moIecuIar bioIogical identification indicated that F1 was Botryosphaeria, F2 was Rhi-zopus oryzae, and F5 was Fusarium oxysporum. When straw was used as carbon source, the CMC enzyme activities of F1, F2 and F5 were 39.2, 31.4 and 40.6 IU/mI, respectiveIy; whiIe the CMC enzyme activity of the mixed cuIture of F1＋F2＋F5 was 50.12 IU/mI, which was increased by 23% compared to that of the singIe straln of F5. The experimental resuIts indicated that the ceI uIose-degrading effect of the compIex microbial system was better than those of the singIe fungi stralns, and the singIe stralns of F1, F2 and F5 had certaln deveIopment potentials.

Direct linear discriminant analysis based on column pivoting QR decomposition and economic SVD

A direct linear discriminant analysis algorithm based on economic singular value decomposition （DLDA/ESVD） is proposed to address the computationally complex problem of the conventional DLDA algorithm, which directly uses ESVD to reduce dimension and extract eigenvectors corresponding to nonzero eigenvalues. Then a DLDA algorithm based on column pivoting orthogonal triangular （QR） decomposition and ESVD （DLDA/QR-ESVD） is proposed to improve the performance of the DLDA/ESVD algorithm by processing a high-dimensional low rank matrix, which uses column pivoting QR decomposition to reduce dimension and ESVD to extract eigenvectors corresponding to nonzero eigenvalues. The experimental results on ORL, FERET and YALE face databases show that the proposed two algorithms can achieve almost the same performance and outperform the conventional DLDA algorithm in terms of computational complexity and training time. In addition, the experimental results on random data matrices show that the DLDA/QR-ESVD algorithm achieves better performance than the DLDA/ESVD algorithm by processing high-dimensional low rank matrices.

基于小波灰度曲面的近红外手指静脉识别方法

针对手指静脉的身份识别问题,并结合手指静脉具有丰富纹理信息的特点,提出了一种基于小波灰度曲面的近红外手指静脉识别方法。采用直方图均衡化方法对原始静脉图像的感兴趣区域进行灰度调整,再用小波分解降维,提取降维后具有不同分辨率的图像,构建待匹配图像。将两幅待匹配图像中的对应像素值相减,得到灰度差曲面。求出该灰度差曲面的方差,将其作为衡量两个手指静脉特征曲面之间距离的依据,并据此判定两个静脉是否来自同一个手指。应用该方法在国内和国外两个图库中使用典型和流行方法进行了对比实验,结果表明,提出的方法用Haar小波降维后可获得具有不同分辨率的图像,在两个图库上的最低等误率(EER)分别为0%和4.6281%,识别时间仅为0.061 s和0.0502 s。该算法具有一定的优势和可行性,且准确性高、安全保密性好、运行速度快。