Benefits and Limitations of Artificial Neural Networks in Process Chromatography Design and Operation
Open Access
Abstract
Due to the progressive digitalization of the industry, more and more data is available not only as digitally stored data but also as online data via standardized interfaces. This not only leads to further improvements in process modeling through more data but also opens up the possibility of linking process models with online data of the process plants. As a result, digital representations of the processes emerge, which are called Digital Twins. To further improve these Digital Twins, process models in general, and the challenging process design and development task itself, the new data availability is paired with recent advancements in the field of machine learning. This paper presents a case study of an ANN for the parameter estimation of a Steric Mass Action (SMA)-based mixed-mode chromatography model. The results are used to exemplify, discuss, and point out the effort/benefit balance of ANN. To set the results in a wider context, the results and use cases of other working groups are also considered by categorizing them and providing background information to further discuss the benefits, effort, and limitations of ANNs in the field of chromatography.Keywords
Funding Information
- Bundesministerium fur Wirtschaft und Energie (BMWi)
- Open Access Publishing Fund of the Clausthal University of Technology
This publication has 66 references indexed in Scilit:
- Process analytical technology (PAT) for biopharmaceuticalsBiotechnology Journal, 2011
- Optimization of Artificial Neural Networks for Modeling of Atorvastatin and Its Impurities Retention in Micellar Liquid ChromatographyChromatographia, 2011
- Neural network modelling of adsorption isothermsAdsorption, 2010
- A Hybrid Model Framework for the Optimization of Preparative Chromatographic ProcessesBiotechnology Progress, 2008
- A Review of the Thermodynamics of Protein Association to Ligands, Protein Adsorption, and Adsorption IsothermsChemical Engineering & Technology, 2008
- Application of artificial neural networks for gradient elution retention modelling in ion chromatographyJournal of Separation Science, 2005
- Neural-network methods for boundary value problems with irregular boundariesIEEE Transactions on Neural Networks, 2000
- Artificial neural networks for solving ordinary and partial differential equationsIEEE Transactions on Neural Networks, 1998
- Development and Evaluation of Flexible Empirical Peak Functions for Processing Chromatographic PeaksAnalytical Chemistry, 1997
- Application of Artificial Neural Networks in the Optimization of HPLC Mobile-Phase ParametersJournal of Liquid Chromatography, 1995