Valerie Bibeau, Lucka Barbeau, Daria Camilla Boffito and Bruno Blais
Article (2023)
Open Acess document in PolyPublie and at official publisher |
|
Open Access to the full text of this document Published Version Terms of Use: Creative Commons Attribution Non-commercial Download (1MB) |
Abstract
The power consumption of the agitator is a critical variable to consider in the design of a mixing system. It is generally evaluated through a dimensionless number known as the power number Nₚ. Multiple empirical equations exist to calculate the power number based on the Reynolds number Re and dimensionless geometrical variables that characterize the tank, the impeller, and the height of the fluid. However, correlations perform poorly outside of the conditions in which they were established. We create a rich database of 100 k computational fluid dynamics (CFD) simulations. We simulate paddle and pitched blade turbines in unbaffled tanks from Re 1 to 100 and use an artificial neural network (ANN) to create a robust and accurate predictor of the power number. We perform a mesh sensitivity analysis to verify the precision of the Nₚ values given by the CFD simulations. To sample the 100 k mixers by their geometrical and physical properties, we use the Latin hypercube sampling (LHS) method. We then normalize the data with a MinMax transformation to put all features in the same scale and thus avoid bias during the ANN's training. Using a grid search cross-validation, we find the best architecture of the ANN that prevents overfitting and underfitting. Finally, we quantify the performance of the ANN by extracting 30% of the database, predicting the Nₚ using the ANN, and evaluating the mean absolute percentage error. The mean absolute error in the ANN prediction is 0.5%, and its accuracy surpasses correlations even for untrained geometries.
Uncontrolled Keywords
artificial neural networks; computational fluid dynamics; mixing; pre-processing methods
Subjects: | 1800 Chemical engineering > 1800 Chemical engineering |
---|---|
Department: | Department of Chemical Engineering |
Research Center: | URPEI - Research Center in Industrial Flow Processes |
PolyPublie URL: | https://publications.polymtl.ca/52352/ |
Journal Title: | Canadian Journal of Chemical Engineering (vol. 101, no. 10) |
Publisher: | Wiley |
DOI: | 10.1002/cjce.24870 |
Official URL: | https://doi.org/10.1002/cjce.24870 |
Date Deposited: | 18 Apr 2023 14:58 |
Last Modified: | 12 Oct 2024 12:33 |
Cite in APA 7: | Bibeau, V., Barbeau, L., Boffito, D. C., & Blais, B. (2023). Artificial neural network to predict the power number of agitated tanks fed by CFD simulations. Canadian Journal of Chemical Engineering, 101(10), 5992-6002. https://doi.org/10.1002/cjce.24870 |
---|---|
Statistics
Total downloads
Downloads per month in the last year
Origin of downloads
Dimensions