Safe model-based design of experiments using Gaussian processes

Abstract

This is a PDF file of an article that has undergone enhancements after acceptance, such as the addition of a cover page and metadata, and formatting for readability, but it is not yet the definitive version of record. This version will undergo additional copyediting, typesetting and review before it is published in its final form, but we are providing this version to give early visibility of the article. Please note that, during the production process, errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain.

Automated kinetic model identification via cloud services using model-based design of experiments

“…In this section, we demonstrate the developed MBDoEdriven cloud-based platform on two pharmaceutical case studies: nucleophilic aromatic substitution (case study 1) and homogeneous amide formation (case study 2). The first case study, characterised by a unique model structure, involves the precise identification of kinetic parameters for a complex reaction mechanism 43 while the second case study requires the development and identification of a new kinetic model. Reaction Chemistry & Engineering Paper…”

“…It should be noted that the parameter estimation and the MBDoE should efficiently be computed in a time frame faster than the duration Δ i using fast optimization techniques. 43 The online redesign step is as fast as the offline design, where the information gathered is exploited only at the end of preliminary experiments, but faster than the sequential design, where preliminary experimentation is paused for a time duration to redesign the subsequent experiment. Specifically, where 4 experiments are initially designed, after the availability of the first 2, experiments are redesigned using MBDoE, while experiment #3 is running.…”

“…More detail about this MBDoE computational approach has been reported. 43 To compare the results of MBDoE, the t-values for the kinetic parameters calculated before and after parameter estimation are provided in Table 2. It should be noticed that originally kinetic parameters for the reaction from para-product to bisproduct (i.e., k 4,ref and E a 4 ) were not statistically significant.…”

Probabilistic framework for optimal experimental campaigns in the presence of operational constraints

“…The formulation by Telen et al 35 also maximizes the expected value of the information criterion subject to probabilistic constraints by applying the sigma-point method 36 to approximate the uncertainty propagation. More recently, Petsagkourakis and Galvanin 37 used Gaussian Process (GP) surrogates to establish a safe experimental space and to approximate the expected value and variance of the experimental information criterion.…”