.png){kind=icon}
.png){kind=icon}
Return
Optimal Experimental Designs for Process Robustness Studies
.png){kind=icon}
PRE
AI
DOI：10.1080/00401706.2025.2580633.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
In process robustness studies, experimenters are interested in comparing the responses at different locations within the normal operating ranges of the process parameters to the response at the target operating condition. Small differences in the responses imply that the manufacturing process is not affected by the expected fluctuations in the process parameters, indicating its robustness. This article proposes an optimal design criterion, named the generalized integrated variance for differences (GI D) criterion, to set up experiments for robustness studies. GI D-optimal designs have broad applications, particularly in pharmaceutical product development and manufacturing. We show that GI D-optimal designs have better predictive performances than other commonly used designs for robustness studies, especially when the experimental region is not symmetric about the target operating condition. In some cases we examined, the alternative designs typically used are roughly only 50% as efficient as GI D-optimal designs. We demonstrate the advantages of tailor-made GI D-optimal designs through two experiments, including an application to a protein fermentation process robustness study.
Keywords:
A-optimal design
Blocked experiment
D-optimal design
I-optimal design
Pharmaceutical quality by design
Process evaluation