An online monitoring-based adaptive quality control framework for a continuous pharmaceutical cyber-physical system

Abstract

In Pharma 4.0, continuous pharmaceutical manufacturing is pivotal for quality control-driven pharmaceutical development. Pharmaceutical quality control (PQC) in a continuous pharmaceutical cyber–physical system (PCPS) plays a crucial role in ensuring the quality of drug products. However, variations or disturbances in raw materials, equipment conditions, or environmental factors may lead to deviations in critical quality attributes of drugs from their acceptable ranges. This article introduces a generalized online monitoring-based adaptive PQC framework for a continuous PCPS, structured around two phases—variational autoencoder-based online process monitoring and data and knowledge fusion driven adaptive PQC based on a fuzzy-rules emulated network. Next, a case study is presented to preliminarily explore the application of the proposed framework in a simulated pharmaceutical feeding–blending-based twin screw granulation process. Finally, a series of simulation experiments are designed to verify the feasibility and effectiveness of the simulation modelling and the proposed PQC framework.