Abstract
The most important contribution of this work is to provide a new quantification method for product quality. A qualitative quality variable can be quantified by using a conventional method, e.g., good=1 and bad=0. However, this quantification method is useless for operating condition optimization, because the quantified variable does not have any physical meaning and thus the desired quality cannot be specified. On the other hand, the proposed method can relate operating condition to product yield by integrating principal component analysis (PCA) and liner discriminant analysis (LDA), and thus it enables us to specify the desired product quality and optimize the operating condition. In addition, a data-driven methodology for improving product quality and yield is proposed. Referred to as Data-Driven Quality Improvement (DDQI), the proposed method can cope with qualitative as well as quantitative quality variables, determine the operating conditions that can achieve the desired product quality, optimize the operating condition under various constraints, and thus can provide useful information to improve product quality. The usefulness of the proposed quantification method and DDQI is demonstrated through an illustrative case study.
