Bayesian Integration of Quality, Maintenance, and Production in Multivariable Pharmaceutical Processes

In the pharmaceutical industry, integrating quality control, maintenance, and production planning is essential for ensuring regulatory compliance and cost efficiency in complex multivariable processes. This study proposes a comprehensive Bayesian‐integrated framework that jointly optimizes multivariate process monitoring, condition‐based maintenance, and production scheduling using Bayesian control charts, multi‐mode failure modeling, and metaheuristic optimization (genetic algorithm and NSGA‐II). Extensive numerical experiments parameterized with real cost and process data from the tablet‐coating line of Alborz Daru Company, a major Iranian pharmaceutical manufacturer, demonstrate that the proposed model consistently outperforms conventional non‐integrated policies, achieving cost savings of 4.6%–6.9% (average 5.6%) across nine realistic scenarios, along with significantly improved average run length performance. Comprehensive sensitivity analysis (varying costs ±50% and failure rates by an order of magnitude) confirms sustained positive savings between 3.2% and 8.1%, highlighting the robustness of the approach under substantial operating variations typical of regulated pharmaceutical environments.