Data based segmentation and summarization for sensor data in semiconductor manufacturing

• Data were classified to discrete-valued or continuous-valued groups.
• Discrete-valued data were segmented with abnormal difference.
• Continuous-valued data were segmented with free knot spline with knot removal.
• Segmentation and summarization were performed based on linearity and parsimony.
• Segmentation had 38.54% error decrease compared to the conventional method.

In semiconductor manufacturing processes, sensor data are segmented and summarized in order to reduce storage space. This is conventionally done by segmenting the data based on predefined chamber step information and calculating statistics within the segments. However, segmentation via chamber steps often do not coincide with actual change points in data, which results in suboptimal summarization. This paper proposes a novel framework using abnormal difference and free knot spline with knot removal, to detect actual data change points and summarize on them. Preliminary experiments demonstrate that the proposed algorithm handles arbitrarily shaped data in a robust fashion and shows better performance than chamber step based segmentation and summarization. An evaluation metric based on linearity and parsimony is also proposed.