Multivariate batch to batch optimisation of fermentation processes incorporating validity constraints

Abstract

This paper presents an innovative optimisation technique, which utilises an adaptive Multiway Partial Least Squares (MPLS) model to track the dynamics of a batch process from one batch to the next. Utilising this model, an optimisation algorithm solves a quadratic cost function that identifies operating conditions for the subsequent batch that should increase yield. Hard constraints are shown to be required when solving the cost function to ensure that batch conditions do not vary too greatly from one batch to the next. Furthermore, validity constraints are imposed to prevent the PLS model from extrapolating significantly when determining new operating conditions. The capabilities of the proposed technique are illustrated through its application to two benchmark fermentation simulations, where its performance is shown to compare favourably with alternative batch-to-batch optimisation techniques.

Multi‐source domains transfer learning strategy based on similarity measurement for batch process quality prediction

“…The synthesis process of cobalt oxalate is a typical batch production process. The liquid phase reaction equation between ammonium oxalate and cobalt chloride in solution is as follows [ 35 ] : …”

History and Evolution of Modeling in Biotechnology: Modeling & Simulation, Application and Hardware Performance

“…The batch to batch optimization strategy was then benchmarked with a fed-batch fermentation simulation of S. cerevisiae . The authors reported an almost 5-fold increase of biomass yield in <20 batches [87] . In 2020 the same authors applied their previously developed multivariate statistical process model to “a realistic industrial-scale fed-batch penicillin simulator” for batch to batch optimization of penicillin yield by adjusting the glucose feed rate [88] .…”