Use of eggshell and coffee grounds in ecological bricks: optimization with artificial neural networks
Submitted: 2025-09-03
|Accepted: 2025-10-01
|Published: 2025-10-20
Copyright (c) 2025 Gudryene dos Santos Ferreira, André Luiz Justi
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Downloads
Keywords:
Soil-Cement Bricks, Eggshell, Coffee Grounds, Compressive Strength, Artificial Neural Networks
Supporting agencies:
Abstract:
Population growth and the increased consumption of materials have generated significant environmental impacts, particularly in the civil construction industry, one of the largest producers of waste. In this context, soil-cement bricks emerge as a sustainable alternative, as they are produced without firing, reducing emissions, and use local soil, offering advantages such as lightness, thermal comfort, and lower cost. This study investigated the influence of adding residues (coffee grounds and eggshells) on the mechanical strength of these bricks. The soil used had a clayey composition, and the bricks were prepared with different proportions of residues (0%, 10%, 30%, and 50%) mixed with cement. After curing, compression tests evaluated their resistance. The results showed that eggshell improved compressive strength, especially at concentrations of 10% and 30%, while coffee grounds hindered homogenization, reducing strength. Eggshell proved promising as a sustainable aggregate. Additionally, Artificial Neural Networks (ANN) were used to optimize material proportions, maximizing strength and minimizing environmental impacts. The ANN modeled the mechanical behavior based on experimental data. This work contributes to the development of eco-friendly materials, highlighting the use of waste as a viable and sustainable alternative for civil construction, and demonstrates the potential of computational methods in innovating construction practices.
References:
Agbemenou, K. H., Motamed, R., & Khoei, A. T. (2024). Prediction of the Nominal Side Resistance of Drilled Shafts in Dominantly Cohesive Soils using ANN. Transportation Research Record, 2679(2), 2162–2175. https://doi.org/10.1177/03611981241273310
Asimakopoulou, F. E., Kontargyri, V. T., Tsekouras, G. J., Gonos, I. F., & Stathopulos, I. A. (2015). Estimation of the Earth Resistance by Artificial Neural Network Model. Transactions on Industry Applications, 51(6), 5149–5158. https://doi.org/10.1109/TIA.2015.2427114
Bal, L., & Buyle-Bodin, F. (2013). Artificial neural network for predicting drying shrinkage of concrete. Construction and Building Materials, 38, 248–254. https://doi.org/10.1016/j.conbuildmat.2012.08.029
Brazilian Agricultural Research Corporation (EMBRAPA). (1997). Soil analysis manual. EMBRAPA.
Brazilian Association of Technical Standards (ABNT). (2012). NBR 8491: Solid soil-cement brick. Rio de Janeiro: ABNT.
Brazilian Association of Technical Standards (ABNT). (2013). NBR 10833: Soil-cement – Compression test. Rio de Janeiro: ABNT.
Brazilian Coffee Industry Association - ABIC. Evolution of coffee consumption in Brazil. https://estatisticas.abic.com.br/estatisticas/indicadores-da-industria/ . Accessed April 3, 2025.
Brazilian Institute of Geography and Statistics - IBGE. (2023). Indicators: egg production. https://www.ibge.gov.br/indicadores . Accessed April 3, 2025.
Brazilian Portland Cement Association - ABCP. (2000). Manufacturing of soil-cement bricks using manual presses (3rd ed.). São Paulo.
Felix, E. F., Balabuch, T. J. R., Posterlli, M. C., Possan, E., & Carrazedo, R. (2018). Analysis of the service life of reinforced concrete structures under uniform corrosion using a model with ANN coupled to FEM. Revista ALCONPAT, 8(1), 1–15. http://dx.doi.org/10.21041/ra.v8i1.256
Garcez, L.R., Lima, M. dos S., Ribas, L.F., Balestra, C.E.T., Monteiro, N.B.R., Melo Filho, J. de A., Gil, M.A.R. (2024). Characteristics of the açai seed (Euterpe precatoria Martius) after thermal processing and its potential in soil-cement brick. Case Studies in Construction Materials, v. 20. https://doi.org/10.1016/j.cscm.2023.e02816
Grande, F. M. (2003). Manufacturing of modular soil-cement bricks by manual pressing with and without the addition of silica fume [Dissertation]. São Paulo University. https://doi.org/10.11606/D.18.2003.tde-07072003-160408
Jordan, R.A., Costa, M.V. da, Martins, E.A.S., Rosa, M.A., & Petrauski, A. (2019). Manufacture of soil-cement bricks with the addition of sugarcane bagasse ash. Engenharia Agrícola, v. 39, p. 26-31. https://doi.org/10.1590/1809-4430-Eng.Agric.v39n1p26-31/2019
Haykin, S. (2007). Neural Networks [electronic resource]: Principles and Practice. 2nd ed. Porto Alegre: Bookman. 898p.
Ladu, L., & Morone, P. (2021). Holistic approach in the evaluation of the sustainability of bio-based products: An Integrated Assessment Tool. Sustainable Production and Consumption, 28, 911–924. https://doi.org/10.1016/j.spc.2021.07.006
Lorenzi, A., Silva, B.V., Barbosa, M.P., Silva Filho, L.C.P. (2017). Artificial neural networks application to predict bond steel-concrete in pull-out tests. IBRACON Structures and Materials Journal, 10(5), 1051-1074. https://doi.org/10.1590/S1983-41952017000500007
Mussatto, S. I., Machado, E. M. S., Martins, S., & Teixeira, J. A. (2011). Production, composition, and application of coffee and its industrial residues. Food and Bioprocess Technology, 4, 661–672. https://doi.org/10.1007/s11947-011-0565-z
Naderpour, H., Poursaeidi, O., & Ahmadi, M. (2018). Shear resistance prediction of concrete beams reinforced by FRP bars using artificial neural networks. Measurement, 126, 299–308. https://doi.org/10.1016/j.measurement.2018.05.051
Queiroz, S.O., Cordeiro, L.N.P., Paes, I.N.L., Bessa, S.A.L., & Braga, R.M.Q.L. (2025). Physical-mechanical performance analysis of soil-cement mixtures incorporating palm biomass ash. In Editora Científica Digital Ltda. (Chapter 30, pp. 621-641). https://doi.org/10.37885/241118232
Rocha, J.H.A., Rosas, M.H., Chileno, N.G.C., & Tapia, G.S.C. (2021). Physical-mechanical assessment for soil-cement blocks including rice husk ash. Case Studies in Construction Materials, v. 14. https://doi.org/10.1016/j.cscm.2021.e00548
Rocha, R. R., Barros, G. H. V., Silva, R. J., & Simões, R. D. (2021). Mechanical strength of adobe bricks reinforced with eggshell waste. Colloquium Exactarum, 13(1), 30–37. https://doi.org/10.5747/ce.2021.v13.n1.e347
Rebello, N., Deekshitha, K., & Shetty, S. (2023). Hydraulically manufactured cement and fly ash stabilized compressed soil block. Materials Today: Proceedings, v. 88, p. 29-34. https://doi.org/10.1016/j.matpr.2023.04.483
Santos, B.C.S. dos, Santos, L.M. dos, Silva, L.H.P., Tamashiro, J.R., & Antunes, P.A. (2022). Fabrication and analysis of soil-cement bricks with the addition of biomass ash from industrial boilers. Brazilian Journal of Development, v. 8, n. 5, p. 33141-33156. https://doi.org/10.34117/bjdv8n5-034
Sathiparan, N., Anburuvel, A., Selvam, V.V., & Vithurshan, P.A. (2023). Potential use of groundnut shell ash in sustainable stabilized earth blocks. Construction and Building Materials, v. 393, p. 132058. https://doi.org/10.1016/j.conbuildmat.2023.132058
Silva, T. R., Cecchin, D., Azevedo, A. R. G., Alexandre, J., Valadão, I. C. R. P., Bernardino, N. A., do Carmo, D. de F., Ferraz, P. F. P. (2021). Soil-cement blocks: a sustainable alternative for the reuse of industrial solid waste. Brazilian Journal of Environmental Sciences, 56(4), 673–686. https://doi.org/10.5327/Z21769478956
Tavares, D.S., Ribeiro, D.A., Junior, T.Y., Lacerda, W.S., Tiradentes, E.T., Teixeira, R.G., Garcia, H.V.S. (2020). Use of artificial neural networks to predict concrete compression strength. Brazilian Journal of Development, 6(7), 42815-42826. https://doi.org/10.34117/bjdv6n7-050
Yadollahi, A., Nazemi, E., Zolfaghari, A., Ajorloo, A.M., (2016). Application of artificial neural network for predicting the optimal mixture of radiation shielding concrete. Progress in Nuclear Energy, 89, 69-77. https://doi.org/10.1016/j.pnucene.2016.02.010
