A new state estimation method for high-mix semiconductor manufacturing processes

In semiconductor manufacturing upstream processes may affect the wafer substrate in a manner that alters performance in downstream operations, and the context within which a process is run may fundamentally change the way the process behaves. Incorporating these influences into a control method ultimately leads to better predictability and improved control performance, because one lot of a specific product may take a very different processing path through the fabrication facility than the next lot of that same product. This paper provides a new method for state estimation in a high-mix manufacturing scenario, based on a random walk model. This model, combined with a moving window approach and least squares solution, provides better estimates for simulated processes with a high-mix of tools and products with many low-runners as compared to alternative methods. An approach combining the Kalman filter and the least squares solution is also developed, with improved results in some cases. In the case of manufacturing data, we modify the model parameters and the weights on processing contexts to get better results.