Version 1
: Received: 5 May 2019 / Approved: 7 May 2019 / Online: 7 May 2019 (11:30:56 CEST)
How to cite:
Mosavi, A.; Shamshirband, S.; Salwana, E.; Chau, K.-W.; Tah, J. H. M. Prediction of Multi-Inputs Bubble Column Reactor Using a Novel Hybrid Model of Computational Fluid Dynamics and Machine Learning. Preprints2019, 2019050079. https://doi.org/10.20944/preprints201905.0079.v1
Mosavi, A.; Shamshirband, S.; Salwana, E.; Chau, K.-W.; Tah, J. H. M. Prediction of Multi-Inputs Bubble Column Reactor Using a Novel Hybrid Model of Computational Fluid Dynamics and Machine Learning. Preprints 2019, 2019050079. https://doi.org/10.20944/preprints201905.0079.v1
Mosavi, A.; Shamshirband, S.; Salwana, E.; Chau, K.-W.; Tah, J. H. M. Prediction of Multi-Inputs Bubble Column Reactor Using a Novel Hybrid Model of Computational Fluid Dynamics and Machine Learning. Preprints2019, 2019050079. https://doi.org/10.20944/preprints201905.0079.v1
APA Style
Mosavi, A., Shamshirband, S., Salwana, E., Chau, K. W., & Tah, J. H. M. (2019). Prediction of Multi-Inputs Bubble Column Reactor Using a Novel Hybrid Model of Computational Fluid Dynamics and Machine Learning. Preprints. https://doi.org/10.20944/preprints201905.0079.v1
Chicago/Turabian Style
Mosavi, A., Kwok-wing Chau and Joseph H. M. Tah. 2019 "Prediction of Multi-Inputs Bubble Column Reactor Using a Novel Hybrid Model of Computational Fluid Dynamics and Machine Learning" Preprints. https://doi.org/10.20944/preprints201905.0079.v1
Abstract
The combination of artificial intelligence algorithms and numerical methods has recently become popular in the prediction of macroscopic and microscopic hydrodynamics parameters of bubble column reactors. The multi inputs and outputs machine learning can cover small phase interactions or large fluid behavior in industrial domains. This numerical combination can develop the smart multiphase bubble column reactor with the ability of low-cost computational time. It can also decrease case studies for the optimization process when big data is appropriately used during learning. There are still many model parameters that need to be optimized for a very accurate artificial algorithm, including data processing and initialization, the combination of inputs and outputs, number of inputs and model tuning parameters. For this study, we aim to train four inputs big data during learning process by an adaptive neuro-fuzzy inference system or adaptive-network-based fuzzy inference system (ANFIS) method, and we consider the superficial gas velocity as one of the input variables, while for the first time, one of the computational fluid dynamics (CFD) outputs named gas velocity is used as an output of the artificial algorithm. The results show that the increasing number of input variables improves the intelligence of the ANFIS method up to , and the number of rules during learning process has a significant effect on the accuracy of this type of modeling. The results also show that propper selection of model parameters results in more accuracy in prediction of the flow characteristics in the column structure.
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.