基于概率关联图挖掘日志中关联规则

关联规则挖掘是指寻找大量数据项集之间有趣的关联或相关关系.是数据挖掘研究的一个重要课题.由于大量数据不停地被收集和存储,因此如何有效地从数据库中挖掘出关联规则获得了研究人员的广泛关注.从Web日志中挖掘用户所访问的页面之间的关联规则,能有效改善网站的结构.提高网站性能和质量,为智能化网站提供有效的依据.     

正负关联规则挖掘的研究

传统的基于支持度-置信度框架的关联规则挖掘方法可能会产生大量不相关的、甚至是误导的关联规则,同时也不能区分正负关联规则。本文提出了一种评价关联规则的可量化标准,进一步提出一种能同时挖掘正负关联规则的框架,实验证明该方法是有效的。     

基于关联规则的多冷水机组系统负荷优化分配

本文以多冷水机组系统为研究对象,对系统采集的大量历史运行数据进行数据处理与分析,采用Apriori频繁项集算法,通过分级挖掘,挖掘在不同运行工况下各台冷水机组运行参数与最小运行能耗之间的关联规则,并以机组运行总能耗最小为目标,提出了一种将粒子群算法与关联规则结合的负荷分配优化方法.仿真验证结果表明:该方法通过优化冷水机...     

基于关联规则的复杂系统稳态运行参数优化

针对系统运行过程中,工况切换可能导致系统运行参数目标值的跃变,进而引发系统运行不稳定的问题,本文提出一种基于关联规则的变工况运行参数稳态优化方法,改进了原有的关联规则挖掘策略,将历史工况作为变工况关联规则挖掘的输入条件之一,以系统运行状态稳定为约束,优化稳态运行参数目标值,并讨论了变工况下系统的准稳态运行条件。以某商场冷水机组为应用案例,在典型工况划分的基础上,采用Apriori算法挖掘冷水机组准稳态运行条件下的主要运行参数与性能指标之间的关联关系并进行优化。仿真结果表明:与原运行方式相比,冷水机组运行综合稳定性在过渡季和夏季分别提高了50.4%和62.7%,能耗分别降低了14.48%和16.5%。     

一种基于多值属性的改进Apriori算法

随着大量需要被挖掘的数据变得越来越复杂,多维关联规则已经成为关联规则挖掘中最实用的内容之一.本文主要介绍了在多维关联规则挖掘过程中,针对同一种属性数据出现重复连接的情况,由此而提出的一种解决方案.通过对多值属性信息进行比较,去除重复连接的属性信息,保留有效信息,减少对数据库的扫描.由此对Apriori算法中连接步进行改进,最后通过布尔型关联规则挖掘数据信息并得到结果.相较于Apriori算法,改进算法能更加快速准确地发现知识,缩短挖掘所用的时间.     

RETE算法的改进及其应用

本文先对Rete模式匹配算法进行了概述,然后又从网络结构对Rete模式匹配算法加以改进和优化,使Rete模式匹配算法更加高效快捷。然后我们又分别从规则引擎介绍了Rete算法的应用。     

制造信息系统中基于遗传算法的关联知识挖掘

通过分析制造信息系统中数据集的特点,运用遗传算法的理论,对传统的关联知识挖掘算法进行了优化,对遗传算法中的系统编码进行了深入研究,并应用于制造信息系统中,进行了数据挖掘和知识发现的尝试,并给出了比较详细的算法描述与实现,之后对相应算法的效率以及优缺点进行了分析,并得到了详细量化的实验数据。通过对遗传算法优化过的关联规则的运用,使得对制造信息系统中大量数据进行挖掘的效率明显提高。     

基于关联规则的恒星光谱数据相关性分析

利用关联规则作为恒星光谱数据相关性分析方法,以VC 和Oracle9i作为开发工具,设计并以程序实现了基于关联规则的恒星光谱数据相关性分析系统,给出了其软件体系结构和模块功能,并对恒星光谱数据的预处理、取样技术、背景知识模板、频繁模式集挖掘算法等关键技术进行了详细描述.最后,通过系统运行结果表明,利用关联规则来描述、分析光谱数据特征和物理化学性质之间存在的相关性是可行的和有价值的.     

分布式数据库中关联规则挖掘的研究

在数据挖掘研究中,关联规则挖掘作为数据挖掘研究中的一个重要部分,引起越来越多的关注。因此,主要研究关联规则挖掘,首先介绍关联规则挖掘的一些基础知识、概念描述等,然后对关联规则挖掘的常用算法进行分类探讨,最后分析其中的几种典型算法。     

个性化包装设计中关联规则挖掘技术的应用

从个性化包装产生的原因出发,分析了个性化包装的特点及个性化包装设计的重要性,阐述了基于关联规则挖掘的个性化包装设计的基本方法,详细说明了关联规则挖掘在个性化包装中应用的关键技术,提出了一种基于关联规则挖掘的个性化包装设计模型,并给出了其关键步骤的实现方法。     

Identification and application of dynamic uncoupling between modifications to vibrating systems

This paper develops and demonstrates a strategy for identifying the lack of dynamic interaction, or coupling, between potential design modifications to a vibrating base structure. Such decoupling may be exploited to efficiently compare the performance of competing engineering designs. In particular, it is shown how different design modifications may be represented as the addition or removal of substructures. When these substructures are uncoupled according to the metric developed here, the computational cost of determining the optimal system design can be greatly reduced. For example, if a designer considers seven possible modifications and wishes to examine all possible combinations of the modifications, 128 possible structures must be analyzed. However, if all modifications are dynamically uncoupled, significant computational effort need only be spent on eight of the possible structures in order to generate the responses for all remaining designs. Example problems demonstrate this cost reduction and illustrate cases where dynamic uncoupling occurs. Copyright © 2016 John Wiley & Sons, Ltd.     

Experimental Designs for Constrained Regions

The familiar factorial, fractional factorial, and response surface designs are designs for regularly-shaped regions of interest, typically cuboidal regions and spherical regions. An irregularly shaped region of experimentation arises in situations where there are constraints on the factor level combinations that can be run or restrictions on portions of the region of exploration. Computer-generated designs based on some optimality criterion are a logical alternative for these problems. We give a brief tutorial on design optimality criteria and show how one of these, the D-optimality criteria, can lead to very reasonable designs for constrained regions of interest. We show through a simulation study that D-optimal designs perform very well with respect to the capability of selecting the correct model and accurately estimating the design factor levels that result in the optimal response.     

Response surface optimization for a nonlinearly constrained irregular experimental design space

Finding optimum conditions for process factors in an engineering optimization problem with response surface functions requires structured data collection using experimental design. When the experimental design space is constrained owing to external factors, its design space may form an asymmetrical and irregular shape and thus standard experimental design methods become ineffective. Computer-generated optimal designs, such as D-optimal designs, provide alternatives. While several iterative exchange algorithms for D-optimal designs are available for a linearly constrained irregular design space, it has not been clearly understood how D-optimal design points need to be generated when the design space is nonlinearly constrained and how response surface models are optimized. This article proposes an algorithm for generating the D-optimal design points that satisfy both feasibility and optimality conditions by using piecewise linear functions on the design space. The D-optimality-based response surface design models are proposed and optimization procedures are then analysed.     

Selecting a near‐optimal design for multiple criteria with improved robustness to different user priorities

In a decision‐making process, relying on only one objective can often lead to oversimplified decisions that ignore important considerations. Incorporating multiple, and likely competing, objectives is critical for balancing trade‐offs on different aspects of performance. When multiple objectives are considered, it is often hard to make a precise decision on how to weight the different objectives when combining their performance for ranking and selecting designs. We show that there are situations when selecting a design with near‐optimality for a broad range of weight combinations of the criteria is a better test selection strategy compared with choosing a design that is strictly optimal under very restricted conditions. We propose a new design selection strategy that identifies several top‐ranked solutions across broad weight combinations using layered Pareto fronts and then selects the final design that offers the best robustness to different user priorities. This method involves identifying multiple leading solutions based on the primary objectives and comparing the alternatives using secondary objectives to make the final decision. We focus on the selection of screening designs because they are widely used both in industrial research, development, and operational testing. The method is illustrated with an example of selecting a single design from a catalog of designs of a fixed size. However, the method can be adapted to more general designed experiment selection problems that involve searching through a large design space.     

Minimum cost design of hybrid composite cylinders with temperature dependent properties

Laminated composite cylinders are optimized with the objective of minimizing the material costs by means of hybridization. They are modelled as thick cylinders working under internal and/or external pressures. The optimal designs are subject to a lower bound on the failure pressure determined by the maximum stress criteria. The cylinders are constructed such that the stress patterns match the material properties by placing the stronger material in high stress areas and the weaker material in low stress areas. The resulting structure is of hybrid construction and the cost minimization is achieved not only by using an inexpensive material but also by minimizing the amount of the expensive material used in the design. The effect of temperature change on the stresses and the material properties is included in the analysis. Numerical results are given for graphite/glass hybrid cylinders and the efficiencies of the designs are shown to be substantial by comparing the costs of hybrid and non-hybrid designs. It is also shown that neglecting the effect of temperature on the stiffness and strength parameters of the materials would lead to underdesign and premature failure.     

Template-assisted nano-patterning: from the submicron scale to the submolecular level

Regular pattern formation based on template synthesis is overviewed from the submicron scale to the submolecular level. Size of patterns of course depends on size of template. Specificity and precision of interaction between the templates and between patterned materials are apparently correlated with the size and precision of patterns.     

异方差随机系数回归模型的最优设计

最优设计方法在工程技术领域和工农业生产中具有广泛的应用．随机系数模型的最优设计研究中通常假定随机误差项具有相同的方差,实际中误差的产生往往与观测点有关,从而具有异方差性质．本文研究一般闭区间设计域上异方差随机系数回归模型的最优近似设计问题．我们获得了最优设计可以在设计域的两个端点处得到的一组充分条件,并进一步证明了当误差项方差具有对称结构且设计域是对称区间时,设计域两个对称端点处的等权重设计同时具有多重最优性质,这时最优设计不依赖于模型中随机误差项的方差结构及随机系数项的方差．     

A PROCEDURE TO SELECT THE BEST MATERIAL COMBINATIONS AND OPTIMALLY DESIGN HYBRID COMPOSITE PLATES FOR MINIMUM WEIGHT AND COST

The optimal layup with least weight or cost for a symmetrically laminated plate subject to a buckling load is determined using a hybrid composite construction. A hybrid construction provides further tailoring capabilities and can meet the weight, cost and strength constraints while a non-hybrid construction may fail to satisfy the design requirements. The objective of the optimization is to minimize either the weight or cost of the plate using the ply angles, layer thicknesses and material combinations as design variables. As the optimization problem contains a large number of continuous (ply angles and thicknesses) and discrete (material combinations) design variables, a -sequential solution procedure is devised in which the optimal variables are computed in different stages. The proposed design method is illustrated using graphite, kevlar and glass epoxy combinations and the efficiencies of the hybrid designs over the non-hybrid ones are computed.     

三维环境下的工程图自适应优化技术

工程图纸是企业生产的重要依据,对三维环境下的工程图纸进行优化以符合企业的要求很有必要。论文利用模型与图纸的关联性,给出了以模型模板和工程图模板为基础的自适应优化原理。提出了模板定制的原则,并给出了模板普通定制与特殊定制的方法,为后续优化奠定基础。详细论述了实现自适应优化的几个关键技术,包括视图定位,比例匹配,尺寸定位与明细栏优化,获得了大型复杂装配体工程图良好的优化效果。     

Nanoparticle assembly into a patterned template by controlling the surface wettability

This study demonstrates a straightforward route for an assembly of colloidal nanoparticles into a desired area in a patterned template, using an evaporation method. An alternative method for fabricating a nanometer-scaled patterned template for the assembly of colloidal nanoparticles and different phenomena of colloidal nanoparticle template assemblies according to the surface wettability are presented. We also suggest that an adequate combination of the surface wettability coupled with the physical confinement afforded by the template should allow colloidal nanoparticle assembly into templates with various patterns.