Correlation coefficient of response variances in compound noise and product array experiments

In robust parameter design, a compound noise experiment has been frequently used for reducing the number of experimental runs compared to a product array experiment. However, the results obtained by the compound noise experiment and the product array experiment are often much different. This paper derives an expression of the correlation coefficient of response variances in the compound noise and the product array experiments, which gives an explanation of that difference.     

Creating catalogues of two-level nonregular fractional factorial designs based on the criteria of generalized aberration

We consider the problem of constructing good two-level nonregular fractional factorial designs. The criteria of minimum G and G₂ aberration are used to rank designs. A general design structure is utilized to provide a solution to this practical, yet challenging, problem. With the help of this design structure, we develop an efficient algorithm for obtaining a collection of good designs based on the aforementioned two criteria. Finally, we present some results for designs of 32 and 40 runs obtained from applying this algorithmic approach.     

An optimal selection of two-level regular single arrays for robust parameter experiments

Efforts have been made in the literature to find optimal single arrays which work best for the robust parameter experiments. However, examples show that in many cases the optimal designs obtained by the existing criteria cloud not attain the maximum number of clear interested effects for robust parameter experiments. In this paper, through a similar way of Zhang et al. (2008) (ZLZA, in short), an aliasing pattern to measure the confounding between the interested effects and other effects for the case of robust parameter designs is introduced. A new criterion for selecting optimal two-level regular single arrays is proposed. In the consideration of the criterion, two rank-orders of effects are suggested: one is based on the interest of experimenters and the other is under the usual effect hierarchy principle. The optimal designs are tabulated in the appendix.     

An MEP.2 plan in 3 factorial experiment and its probability of correct identification

The present work consider the problem of constructing search designs for searching at most two active hidden two-factor interactions in 3ⁿ factorial setup under the assumption that the three-factor and higher-order interactions are negligible. The designs presented here are also capable of estimating all the main effects, general mean and the effects of identified active two-factor interactions. The performance of the designs has been studied in the noisy case by computing probability of correct identification.     

Riordan matrices and higher-dimensional lattice walks

An algebraic combinatorial method is used to count higher-dimensional lattice walks in Z^m${\mathbb{Z}}^m$ that are of length n ending at height k. As a consequence of using the method, Sands’ two-dimensional lattice walk counting problem is generalized to higher dimensions. In addition to Sands’ problem, another subclass of higher-dimensional lattice walks is also counted. Catalan type solutions are obtained and the first moments of the walks are computed. The first moments are then used to compute the average heights of the walks. Asymptotic estimates are also given.     

折射型微透镜列阵制作的一种新途径

介绍了一种制作折射型微透镜列阵的新方法,其主要思想参考了灰阶掩模法。所用掩模板用激光直写制作,通过一次曝光即可在光刻胶上形成折射型微透镜的轮廓,并给出了微透镜轮廓的测试图样。     

相控序列的阵列交织快速生成

相控序列为一种性能优越的新型伪随机序列,长为(2~n-1)~2的PC序列可通过(2~n-1)~2的GMW序列和与相控序列相伴的交错序列交织生成。通过移位产生有限域元素和计算迹函数构造PC序列,分别产生了长为9, 49, 225, 961, 3 969, 16 129的PC序列,并验证了其性质。采用该方法由计算机模拟生成六万多个长为961的PC序列,时间小于12 s。     

基于相似日聚类和贝叶斯神经网络的光伏发电功率预测研究

光伏发电功率的预测是光伏发电规划和运行的基础,因而受到越来越多的重视。文中提出了FCM相似日聚类与智能算法相结合的光伏阵列功率短期预测模型。该方法的思路是首先通过分析影响光伏阵列输出功率的主要因素,对历史数据与预测日气象环境进行模糊分类,并筛选出相似度高的子集作为样本,以提高预测样本的质量;然后通过神经网络映射出特征空间与光伏功率之间的复杂关系,并用贝叶斯理论对神经网络参数进行优化,提高网络的泛化能力。为检验该方法的有效性和精确性,将所提出方法与常用BP神经网络模型对同一仿真算例进行预测,预测结果表明本文提出的预测模型效果更佳。     

基于矩阵奇异值分解的空间谱估计算法

本文提出了一种利用矩阵奇异值分解来作空间谱估计的方法,即对由天线阵获取的数据所构成的数据矩阵作奇异值分解、删除来自噪声的贡献的诸最小奇异值以改善信噪比,并利用噪声奇异向量和天线阵的方向向量正交的性质来计算空间谱。除了奇异值分解算法本身给计算稳定性带来好处外,本方法的谱估计性能和计算量均优于近几年来国外广泛关注的一种谱估计算法——MUSIC算法。本方法可用于高分辨的测向系统中。