Setembro 2023 vol. 10 num. 1 - XXX Simpósio Internacional de Engenharia Automotiva

Trabalho completo - Open Access.

Idioma principal | Segundo idioma

Modelagem robusta da formação de goma em misturas brasileiras de etanol-gasolina com base em planejamento de experimentos e abordagens de redes neurais artificiais

Robust modeling of gum formation in Brazilian ethanol-gasoline blends based on design of experiments and artificial neural networks approaches

PRADELLE, Florian Alain Yannick ; CARVALHO, José Eduardo Sanson Portella de ; SANTOS, Brunno Ferreira dos ; PRADELLE, Renata Nohra Chaar ; TURKOVICS, Franck Turkovics ; PERRIER, Béatrice ; MAIRE, François ;

Trabalho completo:

Este trabalho tem como objetivo predizer a formação da goma, com base em dados experimentais obtidos em testes laboratoriais controlados. As condições testadas seguem abordagens de planejamento de experimentos e permitem medir os teores de goma não lavada ou lavada para diferentes níveis experimentais para a composição de gasolina, concentração de etanol, temperatura e período de envelhecimento. Além disso, o conjunto de dados é usado para treinar modelos de Rede Neural Artificial (RNA) por meio de uma ampla triagem de topologias. Além de sua capacidade de generalizar o impacto dos fatores, os modelos de RNA apresentaram o melhor desempenho, com resíduos tão baixos quanto 2,0%. É importante destacar que o efeito catalítico do etanol na formação da goma que foi especulado pela visualização dos dados disponíveis é previsto pelo modelo. Assim, é possível verificar um efeito catalítico para baixas concentrações de etanol (em torno de 20 vol%) após o envelhecimento. Sem envelhecimento ou após armazenamento a baixa temperatura (aproximadamente 20ºC), observa-se um simples efeito de diluição. Tais conclusões fornecem uma interpretação unificada robusta para justificar a discrepância entre alguns autores da literatura, já que alguns observaram efeitos catalíticos ou de diluição.

Trabalho completo:

This work aims to predict the gum formation, based on experimental data from controlled laboratory tests. The tested conditions follow design of experiments approaches and allow to measure either unwashed or washed gum contents for different gasoline composition, ethanol concentration, storage temperature and ageing period levels. Additionally, the dataset is used to train Artificial Neural Network (ANN) models through a broad screening of topologies. In addition to its ability to generalize the impact of the factors, the ANN models showed the best performance, with residues as low as 2.0%. It is important to highlight that the catalytic effect of ethanol in gum formation that was speculated by visualizing the available data is predicted by the model. Thus, it is possible to verify a catalytic effect for low concentrations of ethanol (around 20 vol%) after ageing. Without ageing or after storage at low temperature (approximately 20ºC), a simple dilution effect is observed. Such conclusions provide a robust unified interpretation to justify the discrepancy between some authors from the literature as some observed either catalytic or dilution effects.

Download (PDF)

Palavras-chave: ,

Palavras-chave: ,

DOI: 10.5151/simea2023-PAP10

Referências bibliográficas
  • [1] " Y.V. Fan, S. Perry, J.J. Klemeš, C.T. Lee, A review on
  • [2] air emissions assessment: Transportation, Journal of Cleaner
  • [3] Production. 194 (2018) 673–684.
  • [4] https://doi.org/10.1016/j.jclepro.2018.05.151.
  • [5] [2] N.D.S.A. Santos, V.R. Roso, A.C.T. Malaquias, J.G.C.
  • [6] Baêta, Internal combustion engines and biofuels: Examining
  • [7] why this robust combination should not be ignored for future
  • [8] sustainable transportation, Renewable and Sustainable
  • [9] Energy Reviews. 148 (2021) 111292.
  • [10] https://doi.org/1016/j.rser.2021.111292.
  • [11] [3] Ministério da Agricultura, Pecuária e Abastecimento do
  • [12] Brasil, Página 17 da Seção 1 do Diário Oficial da União
  • [13] (DOU) de 6 de Março de 2015, (2015).
  • [14] https://www.jusbrasil.com.br/diarios/87237712/dou-secao1-06-03-2015-pg-17 (accessed January 20, 2023).
  • [15] [4] B.D. Batts, A.Z. Fathoni, A literature review on fuel
  • [16] stability studies with particular emphasis on diesel oil,
  • [17] Energy & Fuels. 5 (1991) 2–21.
  • [18] https://doi.org/10.1021/ef00025a001.
  • [19] [5] F. Pradelle, S.L. Braga, A.R.F.A. Martins, F. Turkovics,
  • [20] R.N.C. Pradelle, Gum Formation in Gasoline and Its Blends:
  • [21] A Review, Energy & Fuels. 29 (2015) 7753–7770.
  • [22] https://doi.org/10.1021/acs.energyfuels.5b01894.
  • [23] [6] F. Pradelle, S.L. Braga, A.R.F.A. Martins, F. Turkovics,
  • [24] R.N.C. Pradelle, Certainties and challenges in modeling
  • [25] unwashed and washed gums formation in Brazilian
  • [26] gasoline–ethanol blends, Chemical Engineering Research
  • [27] and Design. 122 (2017) 77–96.
  • [28] https://doi.org/10.1016/j.cherd.2017.03.037.
  • [29] [7] W. Liu, M. Safdari Shadloo, I. Tlili, A. Maleki, Q.-V.
  • [30] Bach, The effect of alcohol–gasoline fuel blends on the
  • [31] engines’ performances and emissions, Fuel. 276 (2020)
  • [32] 117977. https://doi.org/10.1016/j.fuel.2020.117977.
  • [33] [8] C.C. Pereira, V.M.D. Pasa, Effect of Alcohol and Copper
  • [34] Content on the Stability of Automotive Gasoline, Energy &
  • [35] Fuels. 19 (2005) 426–432.
  • [36] https://doi.org/10.1021/ef049849h.
  • [37] [9] E.R. Streva, V.M.D. Pasa, J.R. Sodré, Aging effects on
  • [38] gasoline–ethanol blend properties and composition, Fuel. 90
  • [39] (2011) 215–219. https://doi.org/10.1016/j.fuel.2010.07.056.
  • [40] [10] L.S.G. Teixeira, J.C. Souza, H.C. dos Santos, L.A.M.
  • [41] Pontes, P.R.B. Guimarães, E.V. Sobrinho, R.F. Vianna, The
  • [42] influence of Cu, Fe, Ni, Pb and Zn on gum formation in the
  • [43] Brazilian automotive gasoline, Fuel Processing Technology.
  • [44] 88 (2007) 73–76.
  • [45] https://doi.org/10.1016/j.fuproc.2006.08.008.
  • [46] [11] T. Bamidele, C. Onuigbo-Nweze, M. Osuagwu, A.
  • [47] Azubuike, O. Joel, A. Onyewuchi, Evaluating and Inhibiting
  • [48] Gum Formation Tendencies in Gas Condensates, in: All
  • [49] Days, SPE, Lagos, Nigeria, 2018: p. SPE-193458-MS.
  • [50] https://doi.org/10.2118/193458-MS.
  • [51] [12] C.V. D’Ornellas, The Effect of Ethanol on Gasoline
  • [52] Oxidation Stability, SAE Technical Paper 2001-01-3582 in:
  • [53] 2001: pp. 2001-01–3582. https://doi.org/10.4271/2001-01-
  • [54] 3582.
  • [55] [13] F.A.Y. Pradelle, S.L. Braga, A.R.F.A. Martins, F.Y.
  • [56] Turkovics, R.N.C. De Souza, Experimental Study of the
  • [57] Influence of Ethanol Concentration and Temperature on
  • [58] Gum Formation during Prolonged Storage of Brazilian
  • [59] Gasoline-Ethanol Blends, SAE Technical Paper 2015-36-
  • [60] 0169 in: 2015: pp. 2015-36–0169.
  • [61] https://doi.org/10.4271/2015-36-0169.
  • [62] [14] F. Pradelle, S.L. Braga, A.R.F.A. Martins, F. Turkovics,
  • [63] R.N.C. Pradelle, Modeling of Unwashed and Washed Gum
  • [64] Content in Brazilian Gasoline–Ethanol Blends during
  • [65] Prolonged Storage: Application of a Doehlert Matrix,
  • [66] Energy & Fuels. 30 (2016) 6381–6394.
  • [67] https://doi.org/10.1021/acs.energyfuels.6b01379.
  • [68] [15] Ł. Jęczmionek, B. Danek, M. Pałuchowska, W.
  • [69] Krasodomski, Changes in the Quality of E15–E25 Gasoline
  • [70] during Short-Term Storage up to Four Months, Energy &
  • [71] Fuels. 31 (2017) 504–513.
  • [72] https://doi.org/10.1021/acs.energyfuels.6b01260.
  • [73] [16] A.A.C. Pereira, C.A.C. Olivera, A.G. Merma, R.R.
  • [74] Hacha, B. Ferreira dos Santos, M.L. Torem, Mineral
  • [75] bioflotation optimization: Comparison between artificial
  • [76] neural networks and response surface methodology,
  • [77] Minerals Engineering. 169 (2021) 106983.
  • [78] https://doi.org/10.1016/j.mineng.2021.106983.
  • [79] [17] J.E. Carvalho, F.A.Y. Pradelle, S. Braga, A.R.F.
  • [80] Martins, F. Turkovics, R.N.C. Pradelle, Polynomial and
  • [81] ANN models applied to the formation of gums in Brazilian
  • [82] ethanol–gasoline blends—impact of gasoline composition,
  • [83] ethanol concentration, storage temperature, and aging
  • [84] duration. Neural Computing & Applications (2023).
  • [85] https://doi.org/10.1007/s00521-023-08396-1
  • [86] [18] J.E. Carvalho, F.A.Y. Pradelle, S. Braga, A.R.F.
  • [87] Martins, F. Turkovics, R.N.C. Pradelle, Towards a unified
  • [88] understanding of ethanol impact on gum formation in
  • [89] gasoline-ethanol blends: comparison of experimental results
  • [90] with literature, in: Proceedings of the 25th International
  • [91] Congress of Mechanical Engineering, ABCM, 2019.
  • [92] https://doi.org/10.26678/ABCM.COBEM2019.COB2019-
  • [93] 0207"
Como citar:

PRADELLE, Florian Alain Yannick; CARVALHO, José Eduardo Sanson Portella de; SANTOS, Brunno Ferreira dos; PRADELLE, Renata Nohra Chaar; TURKOVICS, Franck Turkovics; PERRIER, Béatrice; MAIRE, François; "Modelagem robusta da formação de goma em misturas brasileiras de etanol-gasolina com base em planejamento de experimentos e abordagens de redes neurais artificiais", p. 32-41 . In: Anais do XXX Simpósio Internacional de Engenharia Automotiva . São Paulo: Blucher, 2023.
ISSN 2357-7592, DOI 10.5151/simea2023-PAP10

últimos 30 dias | último ano | desde a publicação


downloads


visualizações


indexações