基于数据挖掘的产品质量控制建模方法

在产品质量控制过程中,按统计学观点产品已发生的故障与元器件检测筛选之间存在某种内在的关系。为了有效地发现这些关联规则,建立了质量信息挖掘模型,它包括质量灰色预测挖掘算法和质量灰色关联—关联规则挖掘算法,目标是在质量信息数据库中发现所有置信度大于预定阈值的规则及预测产品质量将来发展趋势。按此模型,建立了面向产品质量信息生成的数据仓库和数据集市,设计了质量灰色预测挖掘模型和质量灰色关联—关联规则数据挖掘流程,并用电子元器件老炼筛选和故障模式归类规律两个算例,验证了算法的合理性。     

关联知识规则在产品质量控制中的应用

将关联规则的数据挖掘技术应用到制造信息系统中,在制造信息系统的数据达到一定量时,通过对产品生产过程中质量检测数据等相关属性的分析,得到有利于企业产品生产正确导向的决策支持信息.阐述了关联规则在质量控制中的具体应用,并以SQL Server 2000数据库作为数据源,实现了相应的算法与接口.     

LED照明产品绿色综合评价体系框架与方法研究

以LED照明产品为研究对象,基于生命周期评价方法,从产品环境影响、能源消耗、资源利用、成本和质量五个属性维建立了LED照明产品绿色综合评价体系框架,在此基础上运用群灰色关联分析提出综合绿色性评价方法以及指标权重计算方法。本评价体系能够提供LED照明产品先进性与绿色性评价分析,为不同LED照明产品选优提供理论依据。     

考虑客户需求偏好的产品创新设计方案多属性决策评价

为了使产品创新设计方案的评价和决策过程充分考虑客户的需求偏好特征,研究了考虑客户需求偏好的产品创新设计方案多属性决策评价方法。基于对客户需求偏好的分析,提出集成Kano模型和粗糙集理论的评价指标权重确定方法,提升了指标权重确定的合理性并使客户需求偏好信息有效地反映到评价过程中。考虑到方案评价中决策信息的模糊性和不确定性,构建了基于粗数决策信息处理的产品创新设计方案多属性决策灰色关联分析模型,通过融入上述指标权重并计算各方案的粗数区间差异系数来实现产品创新设计方案的优选。以电冰箱产品创新设计方案评价决策为例,验证了所提方法的可行性和有效性。     

基于B/S的刀具使用寿命评价体系和方法的研究

首先建立了基于B/S(浏览器/服务器Browser/Server)的刀具使用寿命评价体系结构,形成评价体系数据库,并应用层次分析法确定评价指标的权重;然后通过Internet网从各企业收集刀具使用寿命数据信息添加到数据库中,应用粗集理论的模式识别方法对数据信息去除冗余条件属性和进行决策规则简化,简化后它仅包含那些在决策时所必需的条件属性值,但它具有原始知识系统的所有知识。在此基础上应用灰色关联理论方法进一步对刀具使用寿命进行决策排序;最后开发了基于B/S的刀具使用寿命软件,并通过实例进行了验证。     

小样本条件下火箭贮箱制造质量的一致性评价

火箭产品年产量少,检测数据有限,如何在小样本条件下及时、准确地评价产品制造质量一致性是火箭产品质量控制的重要内容之一。通过研究某型火箭贮箱,建立了1种小样本条件下制造质量一致性评价方法,该方法基于已有的火箭贮箱制造质量一致性评价体系,运用改进遗传灰色预测模型对体系各质量指标对应的检测数据进行处理,借助产生的预测数据扩充了原始样本;利用综合估计法分析扩充后的数据,得到了置信水平更高的单一质量指标一致性评价结果;采用CRITIC方法分析了各质量指标在评价体系内的权重,并通过加权融合的方式,实现了对火箭贮箱整体制造质量的一致性评价;最后结合某型火箭贮箱的检测数据进行了计算和分析,验证了该评价方法的有效性。     

网络化外协加工资源选择的决策框架模型及应用

分析网络化外协加工资源选择过程中决策问题的决策目标,提出包含外协时间、外协质量、外协成本、协作信息交互能力、外协过程技术安全和保密性、外协资源保障能力和外协商知识积累和可持续发展能力等7大目标变量的决策目标体系,建立一种网络化外协加工资源选择的决策框架模型,针对决策过程中信息的隐蔽性、模糊性等特点设计模型求解的灰色关联算法,并针对该算法中评价者主观偏好影响评价指标权重的问题,提出一种基于主观偏好的主观性评价指标权重确定方法.最后,给出一个应用实例,验证该决策目标体系、决策框架模型及求解方法的正确性和实用性.     

一种评估机械产品信息质量的方法

提出了一种基于活动的产品信息质量测评方法。旨在帮助设计、工程与技术人员及时、准确、如实、全面地掌握产品信息，据此做出正确决策，充分发挥信息效用。该方法包括：①描述信息制造活动之间关系的过程模型；②支持过程模型中对象及其属性运算的耦合模型；③产品信息质量的量化评价指标。最后通过一个应用实例说明评价过程。     

一种基于灰色理论的企业信息化水平综合评价方法

对企业信息化水平评价问题进行系统分析,建立企业信息化水平的评价指标体系,用一种基于灰色理论的集成方法进行综合研究,即利用灰色统计的方法建立测评矩阵,并用灰色关联分析来确定相关指标的权重,然后利用模糊方法进行综合评价,使得评价更为科学合理。     

工程机械运行体系综合决策模型研究

针对工程机械运行状况决策这一复杂问题,提出了运行体系评价指标要素和评价标准,基于灰色关联算法并尝试借鉴属性理论和属性综合评价理论,研究了工程机械运行体系的属性综合评价方法,建立了综合决策模型,综合考虑了评价过程中的定性指标及定量指标,为工程机械运行状况评价与决策提供了应用方法及手段。     

可重构制造系统布局规划方案的灰色模糊综合评价方法

针对可重构制造系统布局规划方案的决策问题，提出了面向可重构制造系统布局规划方案的灰色模糊综合评价方法。首先对影响制造系统性能的因素进行分析，建立层次化的综合评价指标体系；然后建立布局方案的仿真模型，利用商业仿真软件获取制造系统动态运行时的定量评价指标数据，并通过专家打分法对制造系统的定性评价指标进行量化，在此基础上，利用灰色关联分析法，确定评价指标的权重；最后采用模糊综合评价法，实现了布局规划方案的综合评价，提高了布局规划方案选择的决策水平。以某研究所机械加工车间为研究对象，验证了该方法的可行性和有效性。     

基于灰色理论的改进FMEA方法在装配工艺改善中的应用

应用模糊理论和灰色理论对传统的失效模式与影响分析(Failure Mode and Effect Analysis,FMEA)方法进行改进,以B公司汽车雷达生产工艺为研究对象,以提高产品质量和降低生产成本为目的,对产品装配工艺过程中的失效模式和影响因素进行分析和工艺改进。利用模糊理论对专家评价语言进行处理,得到各个失效模式的风险优先序数,结合灰色关联分析法,对失效模式的影响因子S、O和D进行计算,确定失效模式的风险优先级,针对不同类型的失效模式采用不同改善措施,并通过实例分析验证了方法的有效性,以达到提高产品质量、降低产品返修率的目的。     

加权灰色关联分析模型及其在机械零件可制造性评估中的应用

研究了一种新的加权灰色关联分析模型 ,并以主客观推理法展开的机械设计零件制造性观察评估体系 ,对设计零件的可制造性进行灰色综合评价 ,为机械设计与制造提供了新的决策方法     

Hole characteristics optimization in Nd:YAG laser micro-drilling of zirconium oxide by grey relation analysis

The use of the Taguchi method with grey relational analysis, to determine the laser micro-drilling parameters with consideration of multiple quality characteristics, is studied in this paper. The effort has been made to minimize the micro-drilling defects, such as hole taper and heat-affected zone width, to produce high-quality micro-drills. The Taguchi method coupled with grey relational analysis is therefore used as statistical design of experiment tools for optimization of both the quality characteristics, simultaneously. The optimal result obtained has been verified with the help of an additional confirmatory experiment. This indicates the application feasibility of the grey–Taguchi technique for continuous improvement in product quality in the manufacturing industry.     

Determination of optimum parameters for multi-performance characteristics in drilling by using grey relational analysis

The theory of grey systems is a new technique for performing prediction, relational analysis and decision making in many areas. In this paper, the use of grey relational analysis for optimising the drilling process parameters for the work piece surface roughness and the burr height is introduced. Various drilling parameters, such as feed rate, cutting speed, drill and point angles of drill were considered. An orthogonal array was used for the experimental design. Optimal machining parameters were determined by the grey relational grade obtained from the grey relational analysis for multi-performance characteristics (the surface roughness and the burr height). Experimental results have shown that the surface roughness and the burr height in the drilling process can be improved effectively through the new approach .     

多传感器数据融合技术在室内环境品质监控系统中的应用

为解决室内环境监控系统在信息处理中的误差和不确定性问题,提出一种多传感器自适应加权数据融合算法及基于模糊集理论融合算法的室内环境品质综合指数判定原则。该算法和判定原则以室内环境监测数据为研究对象,对室内环境品质因素进行综合等级评估,并根据评估结果控制驱动设备动作。实验表明:这种数据融合算法和判定原则是正确的,以此构造的室内环境品质监控系统具有较高的精度。     

A grey-based rough decision-making approach to supplier selection

In this paper, we propose a grey-based rough set approach to deal with the supplier selection in supply chain management. The proposed approach takes advantage of mathematical analysis power of grey system theory while at the same time utilizing data mining and knowledge discovery power of rough set theory. It is suitable to the decision-making under more uncertain environments. We also provide a viewpoint on the attribute values in rough set decision table under the condition that all alternatives are described by linguistic variables that can be expressed in grey number. The most suitable supplier can be determined by grey relational analysis based on grey number. A case of supplier selection was used to validate the proposed approach.     

Application of grey-based Taguchi method for simultaneous optimization of multiple quality characteristics in laser transmission welding process of thermoplastics

In the present work, Taguchi method in combination with grey relational analysis is applied for solving multi-criteria optimization problems in laser transmission welding processes. The welding parameters, namely laser power, welding speed and defocal position are optimized with respect to weld strength and weld width. Using the Taguchi quality design concept, an L16 orthogonal array table is chosen for the experiments. Grey relational analysis is applied to convert the multiple quality characteristics to a single performance characteristic called grey relational grade. Optimal welding parameters are then determined by the Taguchi method using grey relational grade as the quality index. Furthermore, analysis of variance is carried out to identify the most significant factor for the overall output feature of the laser transmission welding process. The results of the confirmation experiment show that the optimal laser transmission welding parameters can be determined effectively so as to improve multiple quality characteristics through this approach.     

加权灰靶决策在产品设计知识动态评价中的应用

为进行知识的有效重用,提出一种基于加权灰靶决策的产品设计知识动态评价模型。设计了由功能和质量两部分指标构成的知识动态评价指标体系,以反映不同角度和不同层次下设计知识的质量状况。提出了加权灰靶决策算法,并在综合分析各种目标重要程度的前提下,通过专家评分法进行加权处理,计算出优势效果解,该算法更符合知识动态评价的特点。最后通过对汽车玻璃检具设计知识的有效评价验证了基于加权灰靶决策的模型在产品设计知识动态评价中的有效性。     

Determination of optimum parameters for multi-performance characteristics in turning by using grey relational analysis

Optimization of multi-criteria problems is a great need of producers to produce precision parts with low costs. Optimization of multi-performance characteristics is more complex compared to optimization of single-performance characteristics. The theory of grey system is a new technique for performing prediction, relational analysis, and decision making in many areas. In this paper, the use of grey relational analysis for optimizing the turning process parameters for the workpiece surface roughness and the chip thickness is introduced. Various turning parameters, such as cutting speed, feed rate, tool nose radius, and concentration of solid–liquid lubricants (minimum-quantity lubricant) were considered. A factorial design with eight added center points was used for the experimental design. Optimal machining parameters were determined by the grey relational grade obtained from the grey relational analysis for multi-performance characteristics (the surface roughness and the chip thickness). The results of confirmation experiments reveal that grey relational analysis coupled with factorial design can effectively be used to obtain the optimal combination of turning parameters. Experimental results have shown that the surface roughness and the chip thickness in the turning process can be improved effectively through the new approach. The minimum surface roughness and smallest chip thickness are 9.83 and 0.32?mm, respectively, obtained at optimal conditions of cutting speed, 1,200?rpm; feed rate, 0.06?mm/rev; nose radius, 0.8?mm; and concentration of solid–liquid lubricant (10% boric acid + SAE-40 base oil).