[article]
| Titre : |
Predicting the non-linear conveying behavior in single-screw extrusion : a comparison of various data-based modeling approaches used with cfd simulations |
| Type de document : |
texte imprimé |
| Auteurs : |
W. Roland, Auteur ; C. Marschik, Auteur ; M. Kommenda, Auteur ; A. Haghofer, Auteur ; S. Dorl, Auteur ; S. Winkler, Auteur |
| Année de publication : |
2021 |
| Article en page(s) : |
p. 529-544 |
| Note générale : |
Bibliogr. |
| Langues : |
Anglais (eng) |
| Catégories : |
Extrudeuse monovis
Matières plastiques -- Extrusion:Polymères -- Extrusion
Prévision, Théorie de la
Rhéologie
Simulation par ordinateur
|
| Index. décimale : |
668.4 Plastiques, vinyles |
| Résumé : |
The traditional approach to modeling the polymer melt flow in single-screw extruders is based on analytical and numerical analyses. Due to increasing computational power, data-driven modeling has grown significantly in popularity in recent years. In this study, we compared and evaluated databased modeling approaches (i. e., gradient-boosted trees, artificial neural networks, and symbolic regression models based on genetic programming) in terms of their ability to predict – within a hybrid modeling framework – the three-dimensional non-linear throughput-pressure relationship of metering channels in single-screw extruders. By applying the theory of similarity to the governing flow equations, we identified the characteristic dimensionless influencing parameters, which we then varied to create a large dataset covering a wide range of possible applications. For each single design point we conducted numerical simulations and obtained the dimensionless flow rate. The large dataset was divided into three independent sets for training, interpolation, and extrapolation, the first being used to generate and the remaining two to evaluate the models. Further, we added two features derived from expert knowledge to the models and analyzed their influence on predictive power. In addition to prediction accuracy and interpolation and extrapolation capabilities, we evaluated model complexity, interpretability, and time required to learn the models. This study provides a rigorous analysis of various data-based modeling approaches applied to simulation data in extrusion. |
| Note de contenu : |
- MELT-CONVEYING SIMULATIONS : Governing equations - Dimensionless representation - Traditional melt-conveying model - Parametric design study - Numerical simulations
DATA-BASED MODELING : Data preparation – Modeling - Modeling results
- Table 1 : Range of values for n, t/Db, and h/w of the new (merged) dataset
- Table 2 : Range of Pp,z depending on the power-law exponent of the merged dataset. The numbers of equidistant steps are 61 and 31, respectively, for the "original" and the “additional" data spaces
- Table 3 : Number of samples per dataset after data splitting
- Table 4 : Value ranges of each feature for the three different datasets
- Table 5 : Model performance for the regression task of predicting ΠV from the influencing parameters
- Table 6 : Model performance for the regression task of predicting ΠV. Comparing the influence of the additional features F1 and F2 on the prediction error
- Table 7 : Performance of the traditional Newtonian melt-conveying models for predicting ΠV
- Table 8 : Model constants for the best performing symbolic regression model
|
| DOI : |
https://doi.org/10.1515/ipp-2020-4094 |
| En ligne : |
https://drive.google.com/file/d/12pNqnSQWNmTVTc1gCK_cszVmf9dWA1eR/view?usp=shari [...] |
| Format de la ressource électronique : |
Pdf |
| Permalink : |
https://e-campus.itech.fr/pmb/opac_css/index.php?lvl=notice_display&id=36520 |
in INTERNATIONAL POLYMER PROCESSING > Vol. 36, N° 5 (2021) . - p. 529-544
[article]
|
Aller sur edunet
Accueil
Ajouter le résultat dans votre panier Affiner la recherchePredicting the non-linear conveying behavior in single-screw extrusion : a comparison of various data-based modeling approaches used with cfd simulations / W. Roland in INTERNATIONAL POLYMER PROCESSING, Vol. 36, N° 5 (2021)
