海洋数据质量检验方案中残差优化选择算法磁

随着信息化的快速发展,海洋数据的获取手段变得多种多样,海洋数据的“量”急剧增大,如何保证海洋大数据的质量问题成为热点。抽样检验是一个较成熟的课题,但适用于海洋数据特性的抽样方案研究较少。结合海洋数据的特点,利用 Skyline 的思想,提出了分批排序的优化抽样检验方案选择算法。通过各抽样检验方案残差的 Skyline 集合,选择优化的质量检验方案,提高海洋数据质量检验精度的同时保证海洋数据的检验费用。     

出口服装产品质量安全过程追溯模式研究

纺织品服装出口量持续增长,国内外贸易摩擦也随之日益加剧,构建出口纺织品服装安全质量的有效质量监管体系,并运用电子化手段实现对出口纺织品服装安全质量的有效追溯和过程关键点控制是出口服装检验监管的发展趋势。在总结检验监管一般模式的基础上,分析一般检验监管模式的弊端。通过课题研究,构建了"设计确认+质量检验监管体系+电子化抽样检验"的新检验监管模式,并建立模型评价电子化抽样检验。最后开发了系统对新检验监管模式进行应用。     

一个面向企业生产质检特定领域可适应性软件的实现

文中针对企业生产部门中质量检验数据管理复杂的特定领域问题,从提高信息系统适应性的角度,结合ERP开发实践,给出了一个适合企业生产质量检验领域实现的质量数据管理系统QDMS模型.模型中主要使用了滞后绑定与元数据技术.最后结合具体应用--水泥厂质检中心质量数据管理系统的实现,对该模型作了进一步的解释和说明.     

海洋大数据分级存储中迁移模型的研究

海洋数据具有规模庞大、种类繁多、结构复杂、时空特性明显等特征,如何高效地对海洋中的大数据进行存储是实现我国海洋数字化以及管理的科学化的关键。传统的数据存储系统面临着高扩展性、高可靠性、高安全性和低成本的挑战。阐述海洋数据的特征,制定海洋中大数据的生命周期;根据海洋中大数据的生命周期图,设计出一种适合于海洋大数据特征的迁移模型,解决了海洋中大数据在分级存储中的数据迁移问题,实现了海洋大数据的高效存储。     

一种针对海洋数据的空间抽样方法

抽样是提高海量海洋数据环境调研、数据挖掘、可视化展示等处理运算效率的有效手段。经典的抽样方法(简单、系统、分层、簇)是针对传统工业产品建立起来的,直接应用于海洋数据则存在效率低,信息冗余、空间分布不均等问题。针对这些问题,提出一种针对海洋数据的空间抽样方法,该方法首先利用海洋数据的相关性对研究区域分层;接着基于海洋数据的空间变异性,设计优化的系统空间抽样方法。实验结果表明,新的空间抽样方法在降低样本信息冗余的同时,兼顾了样本点的空间分布。该方法能有效地获取分布均匀的样本点位信息,且兼顾了样本点之间的变异性,较好地保留了区域内的特征变化信息。     

重抽样优化的快速随机抽样一致性算法

为了快速、准确地对含有高比例外点的数据进行模型参数估计,提出一种重抽样优化的快速RANSAC算法.首先在模型检验之前增设预检验,并采用一种基于样条曲线的损失函数来评价模型的质量;然后通过反复重抽样和模型检验来优化内点集;再依据双阈值对内点集进行渐近提纯;最后利用最优内点集来计算模型的参数.特征匹配和基础矩阵估计的实验结果表明,该算法具有较高的精度和效率;当外点比例高于50%时,运行速度比传统算法提高大于2个数量级.     

考虑空间相关性的数据空间特征提取方法

针对具有空间分布特性的时空数据,首先考虑数据的空间相关性对数据进行空间系统抽样,形成灾害数据空间分布样本;然后考虑样本数据的时间维度,运用粗糙集数据约简方法提取数据的空间特征.空间抽样方法能保证抽样精度、提高抽样效率;基于样本数据的约简技术能在保证数据主要传达信息不丢失的前提下对数据进行有效压缩、极大降低数据量,是解决海洋灾害数据监测花费巨大、数据分析繁杂的一种客观方法.最后,以某浅滩某次海洋灾害时空数据进行仿真,验证了数据简约方法的优良性.     

有混合数据输入的自适应模糊神经推理系统

现有数据建模方法大多依赖于定量的数值信息,而对于数值与分类混合输入的数据建模问题往往根据分类变量组合建立多个子模型,当有多个分类变量输入时易出现子模型数据分布不均匀、训练耗时长等问题.针对上述问题,提出一种具有混合数据输入的自适应模糊神经推理系统模型,在自适应模糊推理系统的基础上,引入激励强度转移矩阵和结论影响矩阵,采用基于高氏距离的减法聚类辨识模型结构,通过混合学习算法训练模型参数,使数值与分类混合数据对模糊规则的前后件参数同时产生作用,共同影响模型输出.仿真实验分析了分类数据对模型规则后件的作用以及结构辨识算法对模糊规则数的影响,与其他几种混合数据建模方法对比表明本文所提出的模型具有较高的预测精度和计算效率.     

异质数据仓库中数据质量管理研究及实现

异质数据仓库中有大量的数据,并且数据来源复杂,因而数据质量问题成为系统所面临的最大的挑战之一.为了保证企业数据仓库中的数据质量,使数据适合于特定的用途,在分析了异质数据仓库环境下存在的数据质量问题及保证数据质量的重要性之后,给出了衡量数据质量的客观度量指标,最后提出了解决数据质量问题的质量元模型的建模方法以及在此模型基础上进行的数据质量管理控制的应用.经检验,结合控制传输Agent和度量Agent的质量元模型可以有效地帮助设计、维护和管理企业从各种异质数据源所获得的数据,具有很大的现实意义.     

APQP质量模块的研究和设计

在传统的ERP的质量模块中对质量控制的模块的设计仅仅理解为物流过程中的进货检验、过程检验和最终检验等相关的质量检验.而质量检验只是质量控制的最早形式.真正的质量控制应包括质量检验在内的包括产品设计和实现过程的先期策划阶段,即APQP的过程.该文对APQP质量模块进行了相关研究,并提出了有关的设计思想.通过对ERP系统的质量模块与APQP、CP、FMEA的整合,使得原有的质量管理模块的外延出现了质的变化,从而使得企业在激烈的竞争当中找到一席之地.     

Inspection error and its effects on single sampling plans with fuzzy parameters

In this paper we have designed an acceptance single sampling plan with inspection errors when the fraction of defective items is a fuzzy number. We have shown that the operating characteristics curve of this plan is like a band having high and low bounds, its width depends on the ambiguity of proportion parameter in the lot when the samples size and acceptance numbers are fixed. A comparison of the single sampling plans with and without inspection errors was done to study the effects upon the characteristics. The results of this comparison show that in the sampling plan with inspection errors, there is a lower operating characteristics band in comparison to a sampling plan without inspection errors for good processing quality. We have also shown that the incorrect classification of a good item reduces the fuzzy probability of acceptance and incorrect classification of a defective item results in a higher fuzzy probability of acceptance.     

Ranking manufacturing processes from the quality management perspective in the automotive industry

The aim of this study is to propose a fuzzy decision‐making model to rank manufacturing processes from the quality management perspective in the automotive industry. This paper proposes a model for improving quality management through the assessment and ranking of manufacturing subprocesses with respect to key performance indicators (KPIs). The developed model, supported with the fuzzy extended ELECTRE III, allows for the determination of subprocesses' rank. An illustrative example indicates that the proposed model could be very useful in everyday business operations as total quality management asset. The model can handle all uncertain and vague input data by applying the theory of fuzzy sets. The research also suggests different managerial implications because it provides an adequate tool for overall quality improvement. The number of treated KPIs is relatively high, so ELECTRE III method gives an advantage over other multicriteria analysis methods because it embraces less subjective thinking and demands slightly less experts' knowledge during the process of decision making and assessment.     

有色冶金过程不确定优化方法探讨

有色冶金过程受原料来源多样、工况条件波动、生产成分变化等因素的影响,存在大量的不确定性,严重影响了冶炼生产的稳定性与可靠性.鉴于此,综述不同类型不确定性优化问题的描述方法,具体包括概率不确定优化问题、模糊不确定优化问题和区间不确定优化问题.通过分析有色冶金生产过程的特点与需求,以3种典型的有色冶金过程不确定优化问题为例,探讨不同类型的有色冶金过程不确定优化方法.针对氧化铝生料浆配料过程的概率不确定优化问题,采用基于Hammersley sequence sampling(HSS)的方法实现不确定模型的确定性转换;针对湿法炼锌除铜过程的模糊不确定优化问题,采用基于模糊规则的方法进行确定性评估;针对锌电解分时供电过程的区间不确定优化问题,采用基于min-max的方法求解鲁棒解.工业运行数据均验证了上述方法的有效性.     

Construction of quality control charts by using probability and fuzzy approaches and an application in a textile company

A method that uses statistical techniques to monitor and control product quality is called statistical process control (SPC), where control charts are test tools frequently used for monitoring the manufacturing process. In this study, statistical quality control and the fuzzy set theory are aimed to combine. As known, fuzzy sets and fuzzy logic are powerful mathematical tools for modeling uncertain systems in industry, nature and humanity; and facilitators for common-sense reasoning in decision making in the absence of complete and precise information. In this basis for a textile firm for monitoring the yarn quality, control charts proposed by Wang and Raz are constructed according to fuzzy theory by considering the quality in terms of grades of conformance as opposed to absolute conformance and nonconformance. And then with the same data for textile company, the control chart based on probability theory is constructed. The results of control charts based on two different approaches are compared. It’s seen that fuzzy theory performs better than probability theory in monitoring the product quality.     

Identification of dynamical systems with a robust interval fuzzy model

In this paper we present a new method of interval fuzzy model identification. The method combines a fuzzy identification methodology with some ideas from linear programming theory. On a finite set of measured data, an optimality criterion that minimizes the maximal estimation error between the data and the proposed fuzzy model output is used. The idea is then extended to modelling the optimal lower and upper bound functions that define the band that contains all the measurement values. This results in a lower and an upper fuzzy model or a fuzzy model with a set of lower and upper parameters. The model is called the interval fuzzy model (INFUMO). The method can be used when describing a family of uncertain nonlinear functions or when the systems with uncertain physical parameters are observed. We believe that the fuzzy interval model can be very efficiently used, especially in fault detection and in robust control design.     

A formal approach for graphically building fuzzy XML model

eXtensible Markup Language (XML) has been the de facto standard of data representation and exchange over the Web. In addition, imprecise and uncertain data are inherent in the real world. Although fuzzy data have been extensively investigated in the context of the relational model, the classical relational database model and its fuzzy extension to date do not satisfy the need of modeling complex objects with imprecision and uncertainty on the Web. On the basis of possibility theory, this paper concentrates on fuzzy information modeling in the fuzzy XML model and the fuzzy IFO model. In particular, the formal approach to mapping a fuzzy IFO model to a fuzzy document-type definition model is developed.     

模糊属性集的粗糙上下近似研究

在知识发现和数据挖掘领域,粗集理论与模糊集合理论都是研究信息系统中知识不完备、不准确问题,两者都可利用观测数据表达知识,进行推理。论文针对传统粗集环境下知识表示模型用固定的属性及属性值来描述对象这一局限,提出利用模糊属性模型对知识表达系统进行信息描述,并给出了模糊属性集的粗糙上下近似模型。     

Uncertain probabilities I: the discrete case

We consider discrete (finite) probability distributions where some of the probability values are uncertain. We model these uncertainties using fuzzy numbers. Then, employing restricted fuzzy arithmetic, we derive the basic laws of fuzzy (uncertain) probability theory. Applications are to the binomial probability distribution and queuing theory.     

决策表中规则获取的不确定性研究

知识获取的不确定性主要来源于有限的分辨能力以及对于数据描述的不确定性。首先将Ｒｏｕｇｈ集理论与不确定问题中的证据理论以及模糊集合理论进行比较,然后介绍不确定性数据的模糊描述。通过引入模糊区别矩阵和扩展近似集方法延伸了Ｒｏｕｇｈ集理论,并从模糊决策表中导出合理的决策规则。