Increasing market demand towards higher product and process quality and efficiency forces companies to think of ways to optimize their production. In the area of high-tech manufacturing products even slight variations of the product state during production can lead to costly and time-consuming rework or even scrap parts. Describing an individual products state along the whole manufacturing process including all relevant information involved for utilization in e.g. in-process adjustments of parameters can be one way to stay competitive. Ideally the gathered information can be directly analyzed and in case of an identified critical trend or event, adequate action, like an alarm, can be triggered. Within this paper, the possibility to generate such a system by using cluster analysis and supervised machine learning on product state data along manufacturing processes will be assessed. Finally, the question will be answered, if this concept is a promising approach to increase quality.
