UPDATE | October 22, 2026
Data-driven manufacturing and digital twins across the biologics network
Biologics manufacturing across facilities and scales requires a clear understanding of process variability to maintain consistent performance. Differences in equipment, operating conditions, and manufacturing scale can affect process behavior, making data-driven approaches increasingly important for process monitoring, prediction, and technology transfer.
This whitepaper explores how Samsung Biologics integrates standardized manufacturing facilities, connected process data, multivariate data analysis (MVDA), computational fluid dynamics (CFD), mechanistic modeling, and AI-based approaches to advance digital-twin capabilities across the manufacturing life cycle.
Key highlights include:
Real-time process monitoring and prediction using multivariate data analysis (MVDA)
Physics-based simulation to support facility-fit assessment, scale-up, and technology transfer
AI-based modeling to identify influential process parameters and favorable operating conditions
Case studies demonstrating titer stability improvement and reduced batch-to-batch variation
Integrated digital-twin capabilities supporting cross-site comparability, process optimization, and predictive process control
Discover how data-driven manufacturing and digital-twin technologies can support more consistent process performance, informed technology transfer, and continuous improvement across a global manufacturing network.
Biologics manufacturing across facilities and scales requires a clear understanding of process variability to maintain consistent performance. Differences in equipment, operating conditions, and manufacturing scale can affect process behavior, making data-driven approaches increasingly important for process monitoring, prediction, and technology transfer.
This whitepaper explores how Samsung Biologics integrates standardized manufacturing facilities, connected process data, multivariate data analysis (MVDA), computational fluid dynamics (CFD), mechanistic modeling, and AI-based approaches to advance digital-twin capabilities across the manufacturing life cycle.
Key highlights include:
- Real-time process monitoring and prediction using multivariate data analysis (MVDA)
- Physics-based simulation to support facility-fit assessment, scale-up, and technology transfer
- AI-based modeling to identify influential process parameters and favorable operating conditions
- Case studies demonstrating titer stability improvement and reduced batch-to-batch variation
- Integrated digital-twin capabilities supporting cross-site comparability, process optimization, and predictive process control
Discover how data-driven manufacturing and digital-twin technologies can support more consistent process performance, informed technology transfer, and continuous improvement across a global manufacturing network.
Related Content