Applying algorithm model as virtual sensors for searching latent issues

I.C. manufacturing comprises hundreds of processes such as diffusion, lithography, thin film and etching which are performed on hundreds of machines. Most of them can be easily identified and analyzed, which is attributed to explicit knowledge. However, some ambiguous information still exists, which is attributed to tacit knowledge. Some of critical information is always neglected and conduct the wrong R&D direction. Applying multivariate statistical analysis as virtual sensors can generate specific results corresponding to the core of the equipment or process, and gets rid of non-accurate information using experience rating. That provides a way to guide R&D engineers and to bring to light the essence of the whole process. In summary, process stabilization and cost saving are the main advantages of virtual sensors.