Page Header
DOI: https://doi.org/10.15332/iteckne.v18i1.2532

Prediction of Compressive Strengths for Rice Husks Ash incorporated concrete, Using Neural Network and Reviews

Predicción de resistencias a la compresión para cáscaras de arroz Hormigón incorporado de ceniza, utilizando redes neuronales y revisión de literatura

Cornelius Ngunjiri Ngandu

Abstract - 164 | PDF - 35

Full Text:

PDF

Abstract(es_ES)

El modelado de hormigón que incorpora desechos agrícolas como la ceniza de cáscara de arroz (RHA) podría mejorar potencialmente la utilización de hormigón verde y la aplicación de materiales de construcción sostenibles. Este artículo evalúa la predicción de la resistencia a la compresión para el material cementoso de ceniza de cáscara de arroz (RHA) incorporado en el hormigón utilizando redes neuronales artificiales (ANN), uno de los diversos métodos de predicción. La investigación se basa en varios estudios experimentales previos.

Las revisiones de la literatura de 72 conjuntos de datos para RHA incorporaron concreto de 15 investigaciones anteriores, se utilizaron y sometieron a modelos ANN, con una tasa de aprendizaje de 0.06 con funciones de activación tanh. Se consideraron cuatro (4) variables de entrada, a saber: - variación de superplastificantes o reductores de agua con respecto al control (%), proporción de agua a aglutinante, porcentaje de RHA y resistencia a la compresión del control. La variable de salida fue la resistencia a la compresión del hormigón incorporado con material cementoso RHA. Se seleccionó la ANN con 15 neuronas en la capa oculta y se indicaron valores generales de 5.10MPa, 0.99, 3.81MPa y 9.73% para el error cuadrático medio de la raíz (RMSE), factor de varianza absoluto (R2), error absoluto medio (MAE) y error de porcentaje absoluto medio (MAPE) respectivamente y para conjuntos de datos de entrenamiento, validación / verificación y pruebas individuales, el RMSE, R2, MAE y MAPE oscilan entre 3.98MPa-6.56MPa, 0.98-0.99, 3.44MPa-4.94MPa y 9.19% - 12,41% respectivamente. En general, tanto el conjunto de datos original como el pronosticado, indicaron valores de resistencia más altos y más bajos para el hormigón de material cementoso incorporado de 5-10% y 15-30% de RHA respectivamente en comparación con las resistencias de control.

Teniendo en cuenta que el estudio utilizó datos de diferentes fuentes y con una amplia gama de resistencias del hormigón, la ANN seleccionada mostró un desempeño relativamente bueno. El estudio proporciona un indicador de que las técnicas de aprendizaje automático podrían predecir con precisión la resistencia del hormigón verde. Según el desempeño del modelo, el porcentaje de materiales cementosos RHA en el concreto y las otras 3 variables de entrada tuvieron un impacto significativo en las resistencias del concreto. Se deben realizar investigaciones futuras para predecir el hormigón verde centrado en una clase de hormigón en particular.

Keywords(es_ES)

métodos de predicción; hormigón; redes neuronales artificiales; revisiones de la literatura

Abstract(en_US)

Modelling of concrete that incorporates agricultural wastes such as rice husk ash (RHA) could potentially enhance utilization of green concrete and application of sustainable construction materials. This paper evaluations compressive strength prediction for rice husk ash (RHA) cementitious material incorporated concrete using artificial neural networks (ANNs) one of the various prediction methods.  The research is based on various previous experimental studies.

Literature reviews of 72 datasets for RHA incorporated concrete from 15 previous researches, were used and subjected to ANNs models, having learning rate of 0.06 with tanh activation functions. Four(4) input variables were considered, namely:- superplasticizer or water reducers variation from control (%), water to binder ratio, percentage of RHA and control compressive strengths. Output variable was compressive strength of RHA cementitious material incorporated concrete. The ANN with 15 neurons in the hidden layer was selected and indicated overall values of 5.10MPa, 0.99, 3.81MPa and 9.73% for the root mean square error (RMSE), absolute factor of variance (R2), mean absolute error (MAE) and mean absolute percentage error (MAPE) respectively and for individual training, validation/checking and testing datasets, the RMSE, R2, MAE and MAPE ranging between 3.98MPa-6.56MPa, 0.98-0.99, 3.44MPa-4.94MPa and 9.19%-12.41% respectively. Generally, both predicted and original dataset, indicated higher and lower strength values for 5-10% and 15-30% RHA incorporated cementitious material concrete respectively compared to the control strengths.

Considering that the study utilized data from different sources and with a wide range of concrete strengths the selected ANN showed relatively good performance. The study provides an indicator that machine learning techniques could accurately predict green concrete strength. Based on model performance the percentage RHA cementitious materials in concrete and the other 3 input variable had a significant impact on concrete strengths. Future research should be conducted to predict green concrete focused on particular concrete class.

Keywords(en_US)

prediction methods; concrete; artificial neural networks; Literature reviews

References


V Chandwani, V Agrawal, R Nagar, and S Singh, “Modeling Slump of Ready Mix Concrete Using Artificial Neural Network,” International Journal of Technology, 2, pp.207-216, 2015

D Sathyan, KB Anand, AJ Prakash, and B Premjith, “Modeling the fresh and hardened stage properties of self-compacting concrete using random kitchen sink algorithm,” International journal of concrete structures and materials, March 2018. DOI: 10.1186/s40069-018-0246-7

J Revathy, P Gajalakshmi, and G Ashwini, “Neural network for the prediction of fresh properties and compressive strength of flowable concrete,” Journal of Urban and environmental engineering, vol. 13 (1), pp. 183-197, 2019, doi:10.4090/juee.2019.v13n1.183197

N Islam, MFM Zain, and M Jamil, “Prediction of strength and slump of rice husk ash incorporated high-performance concrete,” Journal of civil engineering and management,vol. 18 (3). pp. 310-317, 2012. DOI: 10.3846/13923730.2012.698890

M Thiedeitz, W Schmidt, M Härder, and T Kränel, “Performance of rice husk ash as supplementary cementitious material after production in the field and in the lab.,” Materials, 13 (19), 4319, Sept. 2020. doi:10.3390/ma13194319

A Sala, J Torres, RM Gutiérrez, and S Delvesto, “Engineering properties of blended concrete with Colombian rice husk ash and metakaolin”, Ingenieria y competitividad, vol. 15 (2), pp. 225-235, 2013.

I Glushankova, A Ketov, and M Krasnovskikh, L Rudakova, I Vaisman, “Rice Hulls as a Renewable Complex Material Resource,” Resources, 7 (2), 31, May 2018. doi:10.3390/resources7020031

HA Mboya, CK King’ondu, KN Njau, and AL Mrema, “Measurement of pozzolanic activity index of scoria, pumice and rice husk ash as potential supplementary materials for portland cement,” Advances in civil engineering, vol. 2017 Article ID 6952645, 13 pages, Aug. 2017. DOI:https://doi.org/10.1155/2017/6952645

Md Safiuddin, JS West, and KA Soudki, “Air Content of Self-Consolidating Concrete and its Mortar Phase including Rice Husk Ash,” Journal of Civil Engineering and Management, vol. 17 (3). pp. 319-329, 2011. doi:10.3846/13923730.2011.589225

EB Ettah, JG Egbe, ES Ubi, and EE Okon, “Investigation of rice husk ash (RHA) as a Supplement in cement for building application,” Civil Engineering Research Journal, vol. 6 (2):555681, pp. 29-34,July 2018. DOI:10.19080/CERJ.2018.06.555681

CY Kawabata, HS Junior, and J Sousa-Coutinho, “Rick husk derived waste materials as partial replacement in light weight concrete,” Ciênc. Agrotec. Lavras, vol. 36 (5), pp. 567-578, 2012. DOI:10.1590/S1413-70542012000500010

AE Abalaka, “Strength and some durability properties of concrete containing rice husk ash produced in a charcoal incinerator at low specific surface,” International journal of concrete structures and materials, vol. 7 (4), pp 287-293, Dec. 2013. DOI 10.1007/s40069-013-0058-8

JM Marangu, CM M’thiruaine, and M Bediako, “Physicochemical Properties of Hydrated Portland Cement Blended with Rice Husk Ash,” Journal of Chemistry (Hindawi) , Vol. 2020, Article ID 5304745, 10 Pages, 2020. DOI: https://doi.org/10.1155/2020/5304745

MN Amin, S Hissans, K Shahzada, K Khan, and T Bibi, “Pozzolanic reactivity and the influence of rice husk ash on early-age autogenous shrinkage of concrete,” Frontier in materials (Front. Mater.), vol. 6 (150), July 2019. doi:10.3389/fmats.2019.00150.

MP Karthik, GA Arul, VV Sree, B Manikandan, and GM Manasha, “Experimental study on rice husk in concrete by partial replacement,” International Journal of ChemTech Research, vol. 10 (8), pp. 812-819, 2017.

TAR Hussin, and J Parasuraman, “Replacement of cement with commercial available rice husk ash in concrete,” Infrastructure university Kuala Lumpur Research, vol. 6(1), 2018.

CS Feltrin, GC Isaia, and A Lübeck, “Synergic effects between mineral admixtures on strength and microstructure of concretes,” Rev. IBRACON Estrut. Mater. (IBRACON Structures and Materials Journal), vol. 13 (6) el3604, 2020

MB Barbosa, AM Pereira,JL Akasaki, CF Fioriti, JV Fazzan, MM Tashima, JJP Bernebeu, and JLP Melges, “Impact strength and abrasion resistance of high strength concrete with rice husk ash and rubber tires,” Revista IBRACON De Estruturas E Materiais (IBRACON Structures and Materials Journal),vol. 6 (5), pp. 811-820, Oct. 2013.

M Amin, and BA Abdelsalam, “Efficiency of rice husk ash and fly ash as reactivity materials in sustainable concrete,” Sustainable Environmental Research, 29 (30), Nov. 2019. DOI: https://doi.org/10.1186/s42834-019-0035-2

DO Oyejobi, TS Adbulkadir, and V Ajibola, “Investigation of rice husk ash cementitious constituent in concrete,” International journal of agricultural technology, vol. 10 (3), pp. 533-542, 2014.

H Mahmud, MFA Malik, RA Kahar, MFM Zain, and SN Raman, “Mechanical properties and durability of normal and water reduced high strength grade 60 concrete containing rice husk ash,” Journal of advanced concrete technology, vol. 7 (1), pp. 21-30, Feb. 2009. [Online series]. Available: https://www.jstage.jst.go.jp/article/jact/7/1/7_1_21/_pdf/-char/en [Accessed: December 18th 2020]

AA Ramezanianpour, M Mahdi Khani, and Gh Ahmedibeni, “The effect of rice husk on mechanical properties and durability of sustainable concretes,” International journal of civil engineering, vol. 7 (2). pp 83-91, June 2009.

AA Akindahunsi, and O Alade, “Exploiting the potentials of rice husk ash as supplement in cement for construction in Nigeria,” International journal of concrete structures and material, vol. 4 (1), pp 3-8, June 2010. DOI 10.4334/IJCSM.2010.4.1.003

EC Jeong, SY Shin, and YS Kim, “Durability performance of concrete using rice husk ash,” Journal of the Korea Institute of Building Construction, vol. 13 (2), 2013. DOI:http://dx.doi.org/10.5345/jkibc.2013.13.2.139

CY Sung, BI Yoo, KT Kim, HJ Jung, and YI Kim, “An Experimental Study on the Engineering Properties of Concrete with Rice-Husk Ash,” Journ. Agri. Sci. Chungnan Nat’l Univ., Korea, vol. 24 (2), pp. 207-217, 1997.

MH Lee, SJ Kwon, and KT Park, “Mechanical properties in rice husk ash and OPC concrete with coconut fiber addition ratios,” Journal of the Korea Institute of Structural Maintainance and Inspection, vol. 19 (2). pp. 117-124, March 2015. DOI:http://dx.doi.org/10.11112/jksmi.2015.19.2.117

A Hasanzade-Inallu, PH Inallou, and B Eskandarinezhad, “Prediction of compressive strength of concrete with manufactured sand using neural networks and bat algorithm,” Soil structure interaction journal, vol. 4, pp. 52-63, 2019.

A Henigal, E Elbeltgai, M Eldwiny, and M Serry, “Artificial Neural Network Model for Forecasting Concrete Compressive Strength and Slump in Egypt,” Journal of Al Azhar University Engineering Sector, vol. 11 (39), pp. 435-446, April 2016.

J Zhang, Y Zhao, and H Li, “Experimental Investigation and Prediction of Compressive Strength of Ultra-High Performance Concrete Containing Supplementary Cementitious Materials,” Advances in Material Science and Engineering, Volume 2017, Article ID 4563164, 8 pages, Dec. 2017. DOI:https://doi.org/10.1155/2017/4563164

V Chandwani, V Agrawal, and R Nagar, “Modeling Slump of Ready Mix Concrete Using Artificial Neural Network,” Advances in Artificial Neural Systems, Volume 2014, ArticleID 629137, 9 Pages, Nov. 2014. DOI:https://doi.org/10.1155/2014/629137

MA Getahun, SM Shitote, and ZCA Gariy, “Experimental Investigation on Engineering Properties of Concrete Incorporating Reclaimed Asphalt Pavement and Rice Husk Ash,” Buildings, 8, 115, Aug. 2018. DOI:10.3390/buildings8090115

V Cecconello, BRC Sartori, MP Kulakowski, CS Kazmierczak, and M Mancio, “Shrinkage and porosity in concrete produced with recycled concrete aggregate and rice husk ash,” Revista IBRACON De Estruturas E Materiais (IBRACON Structures and Materials Journal),vol. 12 (3), pp. 694-704, Jun. 2019. DOI:10.1590/S1983-41952019000300013

IJ Fernandes, D Calheiro, FAL Sánchez, ALD Camacho, TLAC Rocha, CAM Moraes, and VC Sousa, “Characterization of silica produced from rice husk ash: comparison of purification and processing methods,” Materials Research, 20 (Suppl. 2), pp. 512-518, 2017. DOI: 10.1590/1980-5373-MR-2016-1043

DV Reddy, M Alvarez, and D Arboleda,“Rice husk ash as a sustainable concrete material for marine environment,” in Sixth LACCEI International Latin American and Caribbean conference for Engineering and Technology (LACCEI’ 2008), Tegucigalpa, Honduras, 2008.

GA Habeeb, and H Mahmud, “Study on properties of rice husk ash and its use as cement replacement material,” Materials Research, 13 (2), pp. 185-190, 2010.

Yao X, Xu K, and Liang Y, “Comparing the thermo-physical properties of rice husk and rice straw as feedstock for thermochemical conversion and characterization of their waste ash from combustion,” BioResources, 11 (4), pp. 10549-10564, 2016. DOI: 10.15376/biores.11.4.10549-10564

John W. Eaton, David Bateman, Søren Hauberg, and Rik Wehbring, GNU Octave version 5.2.0 manual: A High-level interactive language for numerical computations, 2019. URL: https.//www.gnu.org/software/octave/doc/v.5.2.0

S. Oman, “A Simple Neural Network in Octave-Part 2,” aimatters.wordpress.com, Jan. 3,2016. [online]. Available: https://aimatters.wordpress.com/2016/01/03/a-simple-neural-network-in-octave-part-2/. [Accessed January 27th 2021]

D. Gupta, “Fundamentals of Deep Learning-Activation Functions and When to Use Them?,” analyticsvidhya, Jan. 30, 2020. [online]. Available: https://www.analyticsvidhya.com/blog/2020/01/fundamentals-deep-learning-activation-functions-when-to-use-them/. [Accessed January 27th 2021]

GeeksforGeeks, “Activation Functions in Neural Networks,” GeeksforGeeks, Last updated 8th October, 2020. [ONLINE]. Available: https://www.geeksforgeeks.org/activation-functions-neural-networks/ [Accessed January 18th, 2020]


Abstract - 164 | PDF - 35

Refbacks

  • There are currently no refbacks.
ISSN: 1692-1798 (impreso)
ISSN: 2393-3483 (en línea)



Imagen