In the context of
Pharma 4.0, pharmaceutical quality control (PQC)
is beset by issues such as uncertainties from ever-changing critical
material attributes and strong coupling between variables in the multi-unit
pharmaceutical tablet manufacturing process (PTMP), and how to timely
adjust the operational variables to deal with such challenges has
become a key problem in PQC. In this study, we propose a novel data-knowledge-driven
modeling and operational adjustment framework for PTMP by integrating
Bayesian network (BN) and case-based reasoning (CBR). At the modeling
level, first, a distributed concept is introduced, i.e., the BN model
for each subunit of PTMP is established in accordance with the operation
process sequence, and the transition variables are given by the BN
model established first and retrieved as the new query for the next
unit. Once the BN models of all subunits are built, they are integrated
into a global BN model. At the operational adjustment level, by taking
the expected critical quality attributes (CQAs) and related prior
information as evidence, the operational adjustment is achieved through
global BN reasoning. Finally, the case study in a sprayed fluidized-bed
granulation-based PTMP demonstrates the feasibility and effectiveness
in improving the terminal CQAs of the proposed method, which is also
compared with other methods to showcase its efficacy and merits.
In the context of Pharma 4.0, a cyber‐physical systems (CPSs)‐based pharmaceutical quality control (PQC) mode holds a critical position in ensuring the quality of drug products. This paper is concerned with a PQC problem with uncertainty embodied in ever‐changing critical material attributes, which present new challenges related to costs and efficiency during pharmaceutical development. So, an event‐triggered data‐ and knowledge‐driven adaptive PQC framework is proposed. First, a data‐ and knowledge‐driven adaptive iterative learning control‐based PQC scheme is developed with the assistance of process knowledge that also contains much additional information reflecting the laws and trends governing process operations. Second, an event‐triggering condition suitable for the PQC tasks is designed and embedded in the controller design to reduce some unnecessary computing and communication loads. Furthermore, the integration of process data and knowledge is used for the adaptive adjustment of control parameters and the determination of initial control directions. Finally, several data experiments illustrate the effectiveness of the proposed methods.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.