An information theory-based approach to data clustering for virtual metrology and soft sensors

Soft Sensors (SSs) are on-line estimators of “hardly to be measured” quantities of a process. The difficulty in measuring can be related to economic or temporal costs that cannot be afforded in a high-intensive manufacturing production. In semiconductor manufacturing this technology goes with the name of Virtual Metrology (VM) systems. While a lot of efforts in research have been produced in the past years to identify the best regression algorithms for these statistical modules, small amount of work has been done to develop algorithms for data clustering of the entire production. This paper contains a new Information Theory-based approach to data clustering for Virtual Metrology and Soft Sensors; the proposed algorithm allows to automatically split the dataset into groups to be equally modeled. The proposed approach has been tested on real industrial dataset