ABSTRACT
Today, the quality of many engineering processes has become of great significance. To improve the final quality of products, different methods have been used thus far. Design of experiments (DOE) and response surface methodology (RSM) have been considered as parts of these methods. This chapter is based on the term RSM introduced by Box and Wilson in 1951. Experimental design is considered as the basic concept of RSM. RSM is a series of mathematical and statistical designs with some benefits, such as developing, improving, and optimizing processes. Robust design is another concept that is a subset of RSM and is used for minimizing external noises or tolerance effects. This chapter proposed two distance-based multiobjective decision making (MODM) approaches called goal programming (GP) and distance-based function for an ideal solution. For a better understanding of these concepts, two illustrative examples were presented, related to the CNC machine and welding (friction stir welding (FSW)) process. This chapter provides a methodology to find a process setting that leads to the most desirable values of quality characteristics called responses. In an FSW example, robust design plays an important role in the final quality of welding. Through this concept, external noises reach their lowest level between two response variables—namely ultimate tensile strength (UTS) and elongation. The results are validated by a two-phase procedure, namely (i) optimization of the statistical model, (ii) comparison of initial design, optimal design, and a revised goal programming model. (iii) Using the MODM and distance-based approach. The first two phases have been applied for the CNC machine process, and finally, the distance-based approach has been taken into account for the FSW process.
