A hybrid workflow for investigating wide DEM parameter spaces

Forgber, Thomas; Khinast, Johannes; Fink, Elisabeth

doi:10.1016/j.powtec.2022.117440

Cited by 11 publications

(2 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the quest to model these complex flows, various simulation methods like the Material Point Method (MPM), Particle Finite Element Method, Smoothed Particle Hydrodynamics (SPH), and Discrete Element Method (DEM) have offered valuable insights. − Particularly, DEM has achieved good accuracy for modeling granular flows at a microscopic level if it is properly calibrated, which depends on the accurate adjustment of the model parameters. Traditionally, this parameter calibration has been handled by Design of Experiment (DoE), a structured approach for systematically exploring the effects of various parameter settings. − Despite its effectiveness in parameter calibration, the approach of DoE does not fully encapsulate the intricate, nonlinear interactions characteristic of granular materials, as it typically focuses on overarching simulation outcomes.…”

Section: Introductionmentioning

confidence: 99%

Integrating Graph Neural Network-Based Surrogate Modeling with Inverse Design for Granular Flows

Jiang,

Byrne,

Glassey

et al. 2024

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

Granular flows are central to a wide range of natural phenomena and industrial processes such as landslides, industrial mixing, and material handling and present intricate particle dynamics challenges. This study introduces a novel approach utilizing a Graph Neural Network-based Simulator (GNS) integrated with an inverse design for optimizing Discrete Element Method (DEM) parameters in granular flow simulations. The GNS model, trained on data sets generated from high-fidelity DEM simulations, exhibits enhanced predictive accuracy and generalization capabilities across various materials and granular collapse scenarios. Methodologically, the study contrasts the GNS approach with conventional Design of Experiment (DoE) methods, highlighting its enhanced computational efficiency and dynamic optimization capacity for complex parameter interactions in granular flows. The results demonstrate the GNS method superiority over the DoE in terms of computational speed and handling intricate parameter relationships. This work offers an advancement in computational techniques for granular flow studies, showing the potential of using differential simulations for realistic problems.

show abstract

Section: Introductionmentioning

confidence: 99%

Integrating Graph Neural Network-Based Surrogate Modeling with Inverse Design for Granular Flows

Jiang,

Byrne,

Glassey

et al. 2024

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

show abstract

“…The review articles by Lou et al, and Nagy et al provide a good overview on the application of ML tools in solid oral dosage forms [ 24 ], and the application of artificial neural networks (ANN) including ML in pharmaceutical manufacturing [ 25 ]. Some specific examples where ML tools were applied in the pharmaceutical industry are process monitoring and control of hot-melt extrusion [ 26 ], understanding tablet properties [ 27 ], the prediction of co-crystal formation [ 28 ], and understanding the parameter space for the calibration of simulations [ 29 ]. Machine learning models have also been widely used in the last few years to predict properties of molecules based on their structure.…”

Section: Introductionmentioning

confidence: 99%

Data-Driven Prediction of the Formation of Co-Amorphous Systems

Fink

Brunsteiner²,

Mitsche

et al. 2023

Pharmaceutics

View full text Add to dashboard Cite

Co-amorphous systems (COAMS) have raised increasing interest in the pharmaceutical industry, since they combine the increased solubility and/or faster dissolution of amorphous forms with the stability of crystalline forms. However, the choice of the co-former is critical for the formation of a COAMS. While some models exist to predict the potential formation of COAMS, they often focus on a limited group of compounds. Here, four classes of combinations of an active pharmaceutical ingredient (API) with (1) another API, (2) an amino acid, (3) an organic acid, or (4) another substance were considered. A model using gradient boosting methods was developed to predict the successful formation of COAMS for all four classes. The model was tested on data not seen during training and predicted 15 out of 19 examples correctly. In addition, the model was used to screen for new COAMS in binary systems of two APIs for inhalation therapy, as diseases such as tuberculosis, asthma, and COPD usually require complex multidrug-therapy. Three of these new API-API combinations were selected for experimental testing and co-processed via milling. The experiments confirmed the predictions of the model in all three cases. This data-driven model will facilitate and expedite the screening phase for new binary COAMS.

show abstract