质量功能展开的系统建模及应用研究

【作者】 李朝玲；

【导师】 高齐圣；

【作者基本信息】 青岛大学 ， 系统理论， 2009， 博士

【摘要】 质量功能展开(Quality Function Deployment,QFD)是一种立足于在产品开发过程中最大限度地满足顾客需求的系统化、用户驱动式的质量保证与改进方法。它以质量屋(House of quality,HOQ)为分解工具,将顾客需求依次分解到产品开发的各阶段,包括产品规划、部件配置、工艺规划及制造要求。从系统的观点看,QFD是一个具有输入、过程和输出的复杂系统,是系统工程思想在产品开发中的重要应用。QFD包括质量屋建立和质量屋决策。本文以QFD基本理论为研究基础,针对产品早期设计阶段质量功能展开中存在的输入信息不确定性和判断的主观性所带来的模糊性问题,应用系统理论中不确定性系统的研究方法,对QFD进行了深入、系统地研究。主要工作如下:提出了一种基于二元语义的质量功能展开中顾客需求的最终重要度确定方法。针对顾客表达信息的模糊性和不确定性,引入二元语义表示语言信息,允许顾客采用不同粒度的语义信息进行评价,给出了不同粒度的二元语义转换的方法,通过二元语义算子进行集结计算确定顾客需求的基本重要度。同时,利用市场竞争性评估和竞争目标对基本重要度进行修正,进而确定顾客需求的最终重要度。提出一个模糊线性规划模型。将HOQ中的各种输入变量看成是语言变量,然后分别建立各语言变量的模糊语言术语集及其对应的模糊数,综合考虑工程特性自相关矩阵和顾客需求与工程特性相关矩阵,建立了顾客满意度最大的模糊线性规划模型。进行QFD的模糊建模,从而优化工程特性目标值。提出一种用模糊DEA确定产品规划质量屋中各工程特性权重的方法。基于绿色设计的思想,在考虑环境和成本的情况下,建立了质量屋。同时采用三角模糊数表示质量屋中的各种元素,提出用模糊DEA确定各工程特性权重。将每一个工程特性看作是一个决策单元,该工程特性与每一顾客需求的关联程度看作是输出指标,环境和成本看作是输入指标,决策单元的效率指标值体现了该工程特性的重要程度。提出一种基于灰色关联分析的质量功能展开方法。在质量屋建立过程中,确定关联矩阵的客观方法是利用质量屋中技术评估矩阵与竞争性评估矩阵确定关联关系,但获得大量数据是很困难的。针对这一问题,将灰色关联度引入QFD,以各项工程特性作为比较数列,各项顾客需求作为参考数列,看成灰色系统,利用灰色关联度确定顾客需求与工程特性的关联矩阵,灰色优势分析确定工程特性权重。考虑质量屋中左墙(WHATs)各项之间的联系,提出了拓展的质量屋和拓展的瀑布模型的概念。引入联立方程模型进行QFD质量屋的建立。联立方程的结构式中,内生变量的系数就是顾客需求(WHATs)自相关矩阵,而外生变量的系数就是修正后的顾客需求和工程特性关联矩阵,通过联立方程的二阶段最小二乘估计可以很容易地确定。联立方程的结构式很好地表示了质量屋的结构。更多还原

【Abstract】 Quality function deployment(QFD) is a customer-driven quality improvement method that aims to meet customer needs in a better way and enhance organizational capabilities.Typically,a QFD system can be broken down into four inter-linked phases to fully deploy the customer needs phase by phase,from customer needs into design requirements,which are also known as engineering characteristics and subsequently into parts characteristics,process plans and production requirements.Each translation uses a chart,called "House of Quality"(HoQ).From the view of system,QFD is a complex system with input,process and output and thus an important application of system engineering in product design.QFD includes the establishment of HoQ and decision making with HoQ.On the basis of the fundamental theory of QFD,to solve the intrinsic infinity that brought by infinite input information and subjective evaluation in the early stage of product design, deep and systematic research is done on QFD with infinity method of system theory.The main contents are summarized as follows:To obtain the final importance ratings of the customer requirements in quality function deployment(QFD),a method based on two-tuple linguistic was proposed.Due to the imprecision and vagueness of people’s perception,the two-tuple linguistic model was introduced in QFD to represent linguistic information.And a convenient method was given to transform different granularity linguistic information.Two-tuple linguistic operators were used to aggregate the information and further determine importance ratings of customer requirements.Moreover,market competitive assessment and competitive target were considered to correct the fundamental importance ratings,and the final importance ratings of the customer requirements were determined based on the combination of the fundamental importance ratings and the correct factors.A fuzzy linear programming(FLP) model is proposed.The input variables are treated as linguistic variable,and then fuzzy linguistic term sets and corresponding fuzzy numbers are established to represent the variables.With respect to all the relationships between the customer needs and engineering characteristics and correlations among the engineering characteristics,A FLP model is established aiming to find the optimal target values of the engineering characteristic to maximize the customer satisfaction.With the fuzzy modeling of QFD,the target values of engineering characteristics can be optimized.A new method to rate the engineering characteristics in house of quality of product planning is proposed based on fuzzy,data envelopment analysis.With respect to the environment and cost,the house of quality is established.At the same time,triangular fuzzy numbers are used to represent all the factors in HoQ.Then,a new method based on fuzzy DEA is used to rate the engineering characteristics,in which,each engineering characteristic is considered to be a decision making unit,the relationships between the engineering characteristic and all the customer needs are regarded as output factors,while effect on the environment and cost are regarded as input factors.The importance of the engineering characteristic is determined by the efficiency score.In the establishing of HoQ,it is an objective method to determine the functional relationship by using technical assesses and competitor analysis matrix in HoQ.To solve the problem of insufficient data,grey correlation analysis is introduced in QFD.It is regarded as a grey system with the customer needs as reference sequences and the engineering characteristics as comparative sequences.Furthermore,the relationship matrix between the customer needs and the engineering characteristics is determined by grey correlation degree and the weights of the engineering characteristics can be determined by grey advantage analysis.With respect to the relationships of the WHATs,extended HoQ and extended waterfall model are proposed.To establish the HoQ,simultaneous equations model is first put forward to establish the house of quality.In the structural equations of simultaneous equations model,the coefficients of the endogenous variables represent the correlation matrix of the customer needs,while the coefficients of the exogenous variables denote the relationship matrix between the customer needs and engineering characteristics.All the coefficients can be easily determined by two-stage least squares estimation of the simultaneous equations model.The structural simultaneous equations model is suitable to represent the structure of the house of quality.更多还原