Robust Product Design: A Modern View of Quality Engineering in Manufacturing Systems

One of the main technological and economic challenges for engineers is designing high-quality products in manufacturing processes. Most of these processes involve many variables, including controllable (design) and uncontrollable (noise) factors. The Robust Design (RD) method employs a collection of mathematical and statistical tools to investigate these variables while minimizing computational effort. RD aims to achieve high product quality from the customers’ perspective while maintaining an acceptable profit margin. This paper provides an overview of RD concepts, methodologies, and optimization approaches, with particular emphasis on their applications in manufacturing systems. The basic concepts of the quality loss function, orthogonal array, and crossed array design are explained. Furthermore, two classifications are presented according to RD methodology: the first based on different types of factors and the second based on different types of data. These classifications play an important role in determining the number of required experimental replications and selecting appropriate data analysis methods. In addition, the integration of RD with advanced optimization techniques, particularly hybrid model-based and metamodel-based approaches, is discussed to demonstrate how these methods can improve design efficiency while reducing computational cost in manufacturing process design and optimization.