Michael Leonard

Identification and Extensions of Quasiconvex Quality Loss Functions

This paper presents a set of related quasiconvex quality loss functions. Characteristics of quasiconvex functions that are desirable for modeling quality loss are noted. Three frequently used univariate quasiconvex quality loss functions are discussed. Bivariate and multivariate quasiconvex quality loss functions are developed. A set of necessary and sufficient conditions is established for the quasiconvexity of multivariate quality loss functions. An industrial product example is used to illustrate the development of a bivariate quadratic quality loss function.

Development of the Hybrid Weight Assessment System for Multiple Quality Attributes

When designing a product or process, a design engineer is often faced with a number of quality attributes and hence prioritizing the quality attributes is an inevitable task. Development of an adequate weight assessment system for multiple attributes in the early stage of design is crucial, since the choice of paths to quality enhancement depends heavily upon the type of weight assessment system used. Although several weight assessment methods are available in the literature, there is room for improvement. Most weight assessment methods reported in the research community have been developed from the perspective of either customers or a design engineer. This article proposes a hybrid weight assessment system by combining the perspectives of both parties, the customer and a design engineer, in such a way that uncertainty of human perceptions can be modeled using the concepts of fuzzy sets and Monte Carlo simulation. A model is presented and a numerical example is discussed.

Development of a Scaling Factor Identification Method Using Design of Experiments for Product-Family-Based Product and Process Design

Identifying the most influential scaling factor is critical in the early stage of product-family-based product design, but the issue has been inadequately address by researchers and not properly applied to real-world manufacturing problems. A scaling fa..