Development of an artificial neural network EMMS drag model for the simulation of fluidized beds in chemical looping combustion

• Published in: Chemical engineering science 2023-12, Vol.282, p.119286, Article 119286
• Main Authors: Stamatopoulos, P., Stefanitsis, D., Zeneli, M., Nikolopoulos, N.
• Format: Article
• Language: English
• Subjects: Artificial Neural Network; CFD; Chemical Looping Combustion; EMMS; Fluidized Beds
• ISSN: 0009-2509
• DOI: 10.1016/j.ces.2023.119286

[Display omitted] •Development of an Artificial Neural Network EMMS drag model to be applied in fluidized bed simulations of chemical looping combustion.•22 representative cases of CLC processes for the training of the ANN resulting in ∼ 6,350,000 individual data points, after interpolation.•Average mean percentage error of less than 15% between the predictions of the ANN-EMMS and the conventional EMMS.•CFD simulations of a 1 MWth air reactor utilizing the developed ANN-EMMS model as well as three existing drag models.•Comparison of the predicted pressure profile with published experimental and numerical data: ANN-EMMS lies closest to the experimental data (10.1% deviation). The current work presents an Artificial Neural Network EMMS (ANN-EMMS) drag scheme, developed specifically for applications related to fluidized bed (FB) reactors in chemical looping combustion (CLC); the examined particles correspond to the main bed materials encountered in CLC: ilmenite, hematite and titanium oxide. The data that feed the model are generated by a custom-built MATLAB code that solves the EMMS equations. The developed ANN-EMMS model, along with three other drag models, i.e. the Gidaspow, the Wen-Yu and the conventional EMMS, are tested for their performance in CFD simulations for the conditions of the 1 MWth pilot scale FB air reactor of TU Darmstadt. The results of the simulations utilizing the ANN-EMMS followed by those of the conventional EMMS are the closest to published experimental data for the pressure profile in the reactor, while the ilmenite conversion as predicted by both models is in good agreement with published numerical data.