Surrogate Modeling for Liquid–Liquid Equilibria Using a Parameterization of the Binodal Curve

Abstract

Computational effort and convergence problems can pose serious challenges when employing advanced thermodynamic models in process simulation and optimization. Data-based surrogate modeling helps to overcome these problems at the cost of additional modeling effort. The present work extends the range of methods for efficient data-based surrogate modeling of liquid-liquid equilibria. A new model formulation is presented that enables smaller surrogates with box-constrained input domains and reduced input dimensions. Sample data are generated efficiently by using numerical continuation. The new methods are demonstrated for the surrogate modeling and optimization of a process for the hydroformylation of 1-decene in a thermomorphic multiphase system.

Hybrid Semi‐parametric Modeling in Separation Processes: A Review

“…A recent review shows the importance of data for the integration of models among different scales . Recent works have shown the capability of GP for global optimization of distillation columns , . These tools can be easily implemented into hybrid schemes.…”

“…The results show a more robust and economically viable reaction‐extraction system compared to the referenced case. This work was later extended to reduce the model dimensionality further, by modeling the binodal curve (instead of the complete two‐phase region) and using numerical continuation . The resulting hybrid model was later globally optimized.…”

A hybrid science‐guided machine learning approach for modeling chemical processes: A review

“…Chopda et al 23 apply integrated process analytical techniques, and modeling and control strategies to enable the continuous manufacturing of monoclonal antibodies. McBride et al 48 classify the hybrid modeling applications in different separation processes in chemical industry, namely, distillation, [49][50][51] crystallization, 52,53 extraction, [54][55][56] floatation, 57,58 filtration, 59 and drying. In an excellent edited volume, Glassey and Stosch 63 discuss some of the key strengths of hybrid modeling in chemical processes, particularly in the prediction of scientifically consistent results beyond the experimentally tested process conditions, which is crucial for process development, scale-up, control and optimization.…”

“…Chopda et al 23 apply integrated process analytical techniques, and modeling and control strategies to enable the continuous manufacturing of monoclonal antibodies. McBride et al 48 classify the hybrid modeling applications in different separation processes in chemical industry, namely, distillation, 49–51 crystallization, 52,53 extraction, 54–56 floatation, 57,58 filtration, 59 and drying 60,61 . Venkatasubramanian 62 gives an excellent exposition of the current state of development and applications of artificial intelligence in chemical engineering.…”

Systematic Selection of Green Solvents and Process Optimization for the Hydroformylation of Long-Chain Olefines

“…The ANN is generated with the "train" command of MATLABs deep learning toolbox. A more thorough description of the algorithm used to generate the surrogate is not the scope of this article and can be found in another publication of the authors in the present special issue of Processes [61].…”