Artificial intelligence for the prediction of the physical and mechanical properties of a compressed earth reinforced by fibers
Autor(a) principal: | |
---|---|
Data de Publicação: | 2023 |
Outros Autores: | , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Revista de Engenharia Química e Química |
Texto Completo: | https://periodicos.ufv.br/jcec/article/view/15910 |
Resumo: | The use of natural fibers as a reinforcing product in the production of compressed earth blocks can be considered as an effective means for the environment and savings. This study presents a prediction a model- and simulation-based approach using artificial neural networks (ANN) to predict tensile strength and compressive strength. of earth-friendly concrete containing different types of natural fibers. A group of data with eight influencing characteristics; cement, fiber, sand, fiber length, fiber tensile strength, clay, silt, age used for model formation and validation were collected from the literature. The output was compressive strength and tensile strength. The combination of root mean square propagation and stochastic propagation gradient descent with the momentum method is used to train the ANN. Using various validation criteria such as coefficient of determination (R), root mean squared error (RMSE) and mean absolute error (MAE), the ANN model was validated and compared to two machine learning (ML) Random Forest (RF) techniques and Multilayer Perceptron (MLP). A sensitivity analysis was also performed to validate the robustness and stability of these models. The experimental results showed that the ANN model performed better than other models and, therefore, it can be used as a suitable approach to predict the compressive strength of environmentally friendly earth concrete. |
id |
UFV-4_a68368eb5a3280b8296a59a14893bdf2 |
---|---|
oai_identifier_str |
oai:ojs.periodicos.ufv.br:article/15910 |
network_acronym_str |
UFV-4 |
network_name_str |
Revista de Engenharia Química e Química |
repository_id_str |
|
spelling |
Artificial intelligence for the prediction of the physical and mechanical properties of a compressed earth reinforced by fibersCompressed earth block .Artificial neural networks .Fibers. Cement. Prediction.Bloque de tierra comprimida. Redes neuronales artificiales. Fibras. Cemento. Predicción.The use of natural fibers as a reinforcing product in the production of compressed earth blocks can be considered as an effective means for the environment and savings. This study presents a prediction a model- and simulation-based approach using artificial neural networks (ANN) to predict tensile strength and compressive strength. of earth-friendly concrete containing different types of natural fibers. A group of data with eight influencing characteristics; cement, fiber, sand, fiber length, fiber tensile strength, clay, silt, age used for model formation and validation were collected from the literature. The output was compressive strength and tensile strength. The combination of root mean square propagation and stochastic propagation gradient descent with the momentum method is used to train the ANN. Using various validation criteria such as coefficient of determination (R), root mean squared error (RMSE) and mean absolute error (MAE), the ANN model was validated and compared to two machine learning (ML) Random Forest (RF) techniques and Multilayer Perceptron (MLP). A sensitivity analysis was also performed to validate the robustness and stability of these models. The experimental results showed that the ANN model performed better than other models and, therefore, it can be used as a suitable approach to predict the compressive strength of environmentally friendly earth concrete. El uso de fibras naturales como producto de refuerzo en la producción de bloques de tierra comprimida puede considerarse como un medio eficaz para el medio ambiente y el ahorro. Este estudio presenta un enfoque basado en un modelo de predicción que utiliza redes neuronales artificiales (ANN) para predecir la resistencia a la compresión y a la tracción del hormigón ecológico que contiene diferentes tipos de fibras naturales. Un grupo de datos con ocho características influyentes; El cemento, la fibra, la arena, la longitud de la fibra, la resistencia a la tracción de la fibra, la arcilla, el limo y la edad utilizada para la formación y validación del modelo se recopilaron de la literatura. El resultado fue la resistencia a la compresión y la resistencia a la tracción. La combinación de propagación cuadrática media y descenso de gradiente de propagación estocástica con el método de impulso se utiliza para entrenar la ANN. Usando varios criterios de validación como el coeficiente de determinación (R), el error cuadrático medio (RMSE) y el error absoluto medio (MAE), el modelo ANN fue validado y comparado con dos técnicas de aprendizaje automático (ML) Random Forest (RF) y multicapa. Perceptrón (MLP). También se realizó un análisis de sensibilidad para validar la robustez y estabilidad de estos modelos. Los resultados experimentales mostraron que el modelo ANN se desempeñó mejor que otros modelos y, por lo tanto, puede usarse como un enfoque adecuado para predecir la resistencia a la compresión del concreto de tierra amigable con el medio ambiente. Universidade Federal de Viçosa - UFV2023-07-06info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfhttps://periodicos.ufv.br/jcec/article/view/1591010.18540/jcecvl9iss4pp15910-01eThe Journal of Engineering and Exact Sciences; Vol. 9 No. 4 (2023); 15910-01eThe Journal of Engineering and Exact Sciences; Vol. 9 Núm. 4 (2023); 15910-01eThe Journal of Engineering and Exact Sciences; v. 9 n. 4 (2023); 15910-01e2527-1075reponame:Revista de Engenharia Química e Químicainstname:Universidade Federal de Viçosa (UFV)instacron:UFVenghttps://periodicos.ufv.br/jcec/article/view/15910/8047Copyright (c) 2023 The Journal of Engineering and Exact Scienceshttps://creativecommons.org/licenses/by/4.0info:eu-repo/semantics/openAccessHoucine, BentegriMohamed , RabehiSamir, KherfaneSarra, Boukansous2023-07-06T18:44:22Zoai:ojs.periodicos.ufv.br:article/15910Revistahttp://www.seer.ufv.br/seer/rbeq2/index.php/req2/indexONGhttps://periodicos.ufv.br/jcec/oaijcec.journal@ufv.br||req2@ufv.br2446-94162446-9416opendoar:2023-07-06T18:44:22Revista de Engenharia Química e Química - Universidade Federal de Viçosa (UFV)false |
dc.title.none.fl_str_mv |
Artificial intelligence for the prediction of the physical and mechanical properties of a compressed earth reinforced by fibers |
title |
Artificial intelligence for the prediction of the physical and mechanical properties of a compressed earth reinforced by fibers |
spellingShingle |
Artificial intelligence for the prediction of the physical and mechanical properties of a compressed earth reinforced by fibers Houcine, Bentegri Compressed earth block .Artificial neural networks .Fibers. Cement. Prediction. Bloque de tierra comprimida. Redes neuronales artificiales. Fibras. Cemento. Predicción. |
title_short |
Artificial intelligence for the prediction of the physical and mechanical properties of a compressed earth reinforced by fibers |
title_full |
Artificial intelligence for the prediction of the physical and mechanical properties of a compressed earth reinforced by fibers |
title_fullStr |
Artificial intelligence for the prediction of the physical and mechanical properties of a compressed earth reinforced by fibers |
title_full_unstemmed |
Artificial intelligence for the prediction of the physical and mechanical properties of a compressed earth reinforced by fibers |
title_sort |
Artificial intelligence for the prediction of the physical and mechanical properties of a compressed earth reinforced by fibers |
author |
Houcine, Bentegri |
author_facet |
Houcine, Bentegri Mohamed , Rabehi Samir, Kherfane Sarra, Boukansous |
author_role |
author |
author2 |
Mohamed , Rabehi Samir, Kherfane Sarra, Boukansous |
author2_role |
author author author |
dc.contributor.author.fl_str_mv |
Houcine, Bentegri Mohamed , Rabehi Samir, Kherfane Sarra, Boukansous |
dc.subject.por.fl_str_mv |
Compressed earth block .Artificial neural networks .Fibers. Cement. Prediction. Bloque de tierra comprimida. Redes neuronales artificiales. Fibras. Cemento. Predicción. |
topic |
Compressed earth block .Artificial neural networks .Fibers. Cement. Prediction. Bloque de tierra comprimida. Redes neuronales artificiales. Fibras. Cemento. Predicción. |
description |
The use of natural fibers as a reinforcing product in the production of compressed earth blocks can be considered as an effective means for the environment and savings. This study presents a prediction a model- and simulation-based approach using artificial neural networks (ANN) to predict tensile strength and compressive strength. of earth-friendly concrete containing different types of natural fibers. A group of data with eight influencing characteristics; cement, fiber, sand, fiber length, fiber tensile strength, clay, silt, age used for model formation and validation were collected from the literature. The output was compressive strength and tensile strength. The combination of root mean square propagation and stochastic propagation gradient descent with the momentum method is used to train the ANN. Using various validation criteria such as coefficient of determination (R), root mean squared error (RMSE) and mean absolute error (MAE), the ANN model was validated and compared to two machine learning (ML) Random Forest (RF) techniques and Multilayer Perceptron (MLP). A sensitivity analysis was also performed to validate the robustness and stability of these models. The experimental results showed that the ANN model performed better than other models and, therefore, it can be used as a suitable approach to predict the compressive strength of environmentally friendly earth concrete. |
publishDate |
2023 |
dc.date.none.fl_str_mv |
2023-07-06 |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
https://periodicos.ufv.br/jcec/article/view/15910 10.18540/jcecvl9iss4pp15910-01e |
url |
https://periodicos.ufv.br/jcec/article/view/15910 |
identifier_str_mv |
10.18540/jcecvl9iss4pp15910-01e |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
https://periodicos.ufv.br/jcec/article/view/15910/8047 |
dc.rights.driver.fl_str_mv |
Copyright (c) 2023 The Journal of Engineering and Exact Sciences https://creativecommons.org/licenses/by/4.0 info:eu-repo/semantics/openAccess |
rights_invalid_str_mv |
Copyright (c) 2023 The Journal of Engineering and Exact Sciences https://creativecommons.org/licenses/by/4.0 |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.publisher.none.fl_str_mv |
Universidade Federal de Viçosa - UFV |
publisher.none.fl_str_mv |
Universidade Federal de Viçosa - UFV |
dc.source.none.fl_str_mv |
The Journal of Engineering and Exact Sciences; Vol. 9 No. 4 (2023); 15910-01e The Journal of Engineering and Exact Sciences; Vol. 9 Núm. 4 (2023); 15910-01e The Journal of Engineering and Exact Sciences; v. 9 n. 4 (2023); 15910-01e 2527-1075 reponame:Revista de Engenharia Química e Química instname:Universidade Federal de Viçosa (UFV) instacron:UFV |
instname_str |
Universidade Federal de Viçosa (UFV) |
instacron_str |
UFV |
institution |
UFV |
reponame_str |
Revista de Engenharia Química e Química |
collection |
Revista de Engenharia Química e Química |
repository.name.fl_str_mv |
Revista de Engenharia Química e Química - Universidade Federal de Viçosa (UFV) |
repository.mail.fl_str_mv |
jcec.journal@ufv.br||req2@ufv.br |
_version_ |
1800211191226695680 |