A physics-informed Run-to-Run control framework for semiconductor manufacturing

An interpretable unsupervised Bayesian network model for fault detection and diagnosis

“…In addition to identifying the arcs from data, the algorithm also provides the flexibility to integrate predefined directions on specific arcs. Based on the domain knowledge, the arcs that present known causalities can be defined as a whitelist, and the arcs that present infeasible causalities will be defined as a blacklist (Scutari, 2009;Yang et al, 2020). During the structure learning procedure, any movement against either whitelist or blacklist will be viewed as a violation.…”

Virtual metrology as an approach for product quality estimation in Industry 4.0: a systematic review and integrative conceptual framework

“…Based on a problem-dependent heuristic threshold, the abnormality can be detected. One advantage of calculating the confidence is that besides DD, it can be leveraged to enhance both the quality estimators (Azamfar, Li, and Lee 2020) and machine control algorithms (W. T. Yang et al 2020;Kim, Jang, and Kim 2020). The automatic virtual metrology (AVM) solutions propose an add-on heuristic approach called the reliance index, which is based on the crossover of two different quality estimators (Cheng et al 2008).…”

“…This allows a slow incremental drift to be detected and compensated for (Khakifirooz, Fathi, and Chien 2018). Another approach integrates knowledge about equipment condition into a dEWMA, which is estimated by a dynamic Bayesian network (Yang et al 2020). The main limitation of the EWMA/dEWMA filter is its assumption of linearity and its run-to-run implementation.…”