Estimation of the temperature profiles of reinforced concrete cross sections exposed to standard fires by using artificial neural networks with different topologies

2015 ◽  
Vol 40 (5) ◽  
pp. 655-667
Author(s):  
Selahattin Albayrak ◽  
Oğuz Burnaz
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Reinforced Concrete ◽  
Cross Sections ◽  
Temperature Profiles ◽  
Artificial Neural

scholarly journals Use of Nondestructive Testing of Ultrasound and Artificial Neural Networks to Estimate Compressive Strength of Concrete

Buildings ◽  
2021 ◽  
Vol 11 (2) ◽  
pp. 44
Author(s):  
Fernando A. N. Silva ◽  
João M. P. Q. Delgado ◽  
Rosely S. Cavalcanti ◽  
António C. Azevedo ◽  
Ana S. Guimarães ◽  
...  
Keyword(s):  
Neural Networks ◽  
Compressive Strength ◽  
Artificial Neural Networks ◽  
Cross Sections ◽  
Influential Factors ◽  
Average Error ◽  
Ann Model ◽  
Cement Ratio ◽  
Water Cement Ratio ◽  
Artificial Neural

The work presents the results of an experimental campaign carried out on concrete elements in order to investigate the potential of using artificial neural networks (ANNs) to estimate the compressive strength based on relevant parameters, such as the water–cement ratio, aggregate–cement ratio, age of testing, and percentage cement/metakaolin ratios (5% and 10%). We prepared 162 cylindrical concrete specimens with dimensions of 10 cm in diameter and 20 cm in height and 27 prismatic specimens with cross sections measuring 25 and 50 cm in length, with 9 different concrete mixture proportions. A longitudinal transducer with a frequency of 54 kHz was used to measure the ultrasonic velocities. An ANN model was developed, different ANN configurations were tested and compared to identify the best ANN model. Using this model, it was possible to assess the contribution of each input variable to the compressive strength of the tested concretes. The results indicate an excellent performance of the ANN model developed to predict compressive strength from the input parameters studied, with an average error less than 5%. Together, the water–cement ratio and the percentage of metakaolin were shown to be the most influential factors for the compressive strength value predicted by the developed ANN model.

scholarly journals Red Neuronal Artificial para estimar la resistencia a compresión, en concretos fibro-reforzados con polipropileno [Artificial neural network to predict the compressive strength, in polypropylene fiber-reinforced concrete]

2012 ◽  
Author(s):  
Luis Octavio González Salcedo ◽  
Aydee Patricia Guerrero Zúñiga ◽  
Silvio Delvasto Arjona ◽  
Adrián Luis Ernesto Will
Keyword(s):  
Neural Networks ◽  
Compressive Strength ◽  
Artificial Neural Networks ◽  
Reinforced Concrete ◽  
Polypropylene Fiber ◽  
Stability Control ◽  
Fiber Reinforced Concrete ◽  
Fiber Reinforced ◽  
Artificial Neural ◽  
Polypropylene Fiber Reinforced Concrete

Resumen En diseño y construcción de estructuras de concreto, la resistencia a compresión lograda a los 28 días, es la especificación de control de estabilidad de la obra. La inclusión de fibras como reforzamiento de la matriz cementicia, ha permitido una ganancia en sus propiedades, además de la obtención de un material de alto desempeño; sin embargo, la resistencia a compresión sigue siendo la especificación a cumplir en la normatividad de la construcción. Las redes neuronales artificiales, como un símil de las neuronas biológicas, han sido utilizadas como herramientas de predicción de la resistencia a compresión en el concreto sin fibra. Los antecedentes en este uso, muestran que es de interés el desarrollo de aplicaciones en los concretos reforzados con fibras. En el presente trabajo, redes neuronales artificiales han sido elaboradas para predecir la resistencia a compresión en concretos reforzados con fibras de polipropileno. Los resultados de los indicadores de desempeño muestran que las redes neuronales artificiales elaboradas pueden realizar una aproximación adecuada al valor real de la propiedad mecánica, abriendo una futura e interesante agenda de investigación. Palabras ClavesResistencia a compresión; concreto reforzado con fibras; fibra de polipropileno; predicción; inteligencia artificial; redes neuronales artificiales.   Abstract In concrete structures’ design and construction, the compressive strength achieved at 28 days, is the work’s stability control specification. The inclusion of reinforcing fibers into the cementicious matrix, has allowed a gain in their properties, as well as obtaining a high performance material, however, the compressive strength remains the specification to meet the construction regulations. Artificial neural networks as a biological neurons’ simile have been used as tools for predicting the plain concrete compressive strength. The backgrounds in this application show that interest is the development of applications in fiber-reinforced concrete. In this paper, artificial neural networks have been developed to predict the compressive strength in polypropylene fiber reinforced concrete. The results of the performance indicators show that the developed artificial neural networks can perform an adequate approximation to the actual value of the mechanical property, opening an interesting future research.KeywordsCompressive strength, fiber-reinforced concrete, polypropylene fiber, prediction, artificial intelligence, artificial neural networks.

scholarly journals FEW-GROUP CROSS SECTIONS MODELING BY ARTIFICIAL NEURAL NETWORKS

2021 ◽  
Vol 247 ◽  
pp. 06029
Author(s):  
E. Szames ◽  
K. Ammar ◽  
D. Tomatis ◽  
J.M. Martinez
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Cross Sections ◽  
Linear Interpolation ◽  
Sensitivity Study ◽  
Library Size ◽  
Training Time ◽  
Learning Framework ◽  
Artificial Neural ◽  
And Training

This work deals with the modeling of homogenized few-group cross sections by Artificial Neural Networks (ANN). A comprehensive sensitivity study on data normalization, network architectures and training hyper-parameters specifically for Deep and Shallow Feed Forward ANN is presented. The optimal models in terms of reduction in the library size and training time are compared to multi-linear interpolation on a Cartesian grid. The use case is provided by the OECD-NEA Burn-up Credit Criticality Benchmark [1]. The Pytorch [2] machine learning framework is used.

Prediction of the residual flexural strength of fiber reinforced concrete using artificial neural networks

2021 ◽  
Vol 303 ◽  
pp. 124502
Author(s):  
Marcello Congro ◽  
Vitor Moreira de Alencar Monteiro ◽  
Amanda L.T. Brandão ◽  
Brunno F. dos Santos ◽  
Deane Roehl ◽  
...  
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Reinforced Concrete ◽  
Flexural Strength ◽  
Fiber Reinforced Concrete ◽  
Fiber Reinforced ◽  
Artificial Neural
Sign in / Sign up

Export Citation Format

Share Document