A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Prediction of splitting tensile strength of high strength fiber reinforced self compacting concrete using artificial neural networks
Normal concretes have lesser value of Splitting Tensile Strength when compared to High Strength Fiber Reinforced Self Compacting (HSFRSC) concrete. Filling of formwork even in congested reinforcement and compaction without vibration are the properties of Self-compacting concrete (SCC) in fresh state. From the literature it was observed that finding tensile strength of the HSFRSC concrete has mainly concentrated towards using direct tensile strength test or flexural tensile strength test. There has been very little work carried out to determine it using splitting tensile strength test. There are no uniform and standard code procedures to evaluate the splitting tensile strength HSFRSC concrete. To overcome the difficulty an attempt is made to predict the splitting tensile strength of (HSFRSC) concrete using Artificial Neural Networks (ANN). For solving regression problems ANN are useful Machine Learning (ML) algorithms. In the present study high strength concretes were prepared with three different binder contents of 500 kg/m3, 550 kg/m3 and 600 kg/m3 each of which having several Silica Fume (SF) ratios (0 - 15 %) and Fiber Contents (FC) ratios (0 – 1%). The splitting tensile strength was determined at 7 and 28 days making a total of 54 data sets. Back propagation ANN with all the algorithms available under Neural Networks tool box of MATLAB software are made use of for training, testing and validation of the data sets. To train the Neural Networks, hidden neurons from 10 – 50 in the interval of 10 are used. Predicting the splitting tensile strength of HSFRSC concrete can be done by using ANN effectively. The study demonstrates that the Artificial Neural Networks techniques are effective in Application of this technique will contribute significantly to the concrete quality assurance.
Prediction of splitting tensile strength of high strength fiber reinforced self compacting concrete using artificial neural networks
Normal concretes have lesser value of Splitting Tensile Strength when compared to High Strength Fiber Reinforced Self Compacting (HSFRSC) concrete. Filling of formwork even in congested reinforcement and compaction without vibration are the properties of Self-compacting concrete (SCC) in fresh state. From the literature it was observed that finding tensile strength of the HSFRSC concrete has mainly concentrated towards using direct tensile strength test or flexural tensile strength test. There has been very little work carried out to determine it using splitting tensile strength test. There are no uniform and standard code procedures to evaluate the splitting tensile strength HSFRSC concrete. To overcome the difficulty an attempt is made to predict the splitting tensile strength of (HSFRSC) concrete using Artificial Neural Networks (ANN). For solving regression problems ANN are useful Machine Learning (ML) algorithms. In the present study high strength concretes were prepared with three different binder contents of 500 kg/m3, 550 kg/m3 and 600 kg/m3 each of which having several Silica Fume (SF) ratios (0 - 15 %) and Fiber Contents (FC) ratios (0 – 1%). The splitting tensile strength was determined at 7 and 28 days making a total of 54 data sets. Back propagation ANN with all the algorithms available under Neural Networks tool box of MATLAB software are made use of for training, testing and validation of the data sets. To train the Neural Networks, hidden neurons from 10 – 50 in the interval of 10 are used. Predicting the splitting tensile strength of HSFRSC concrete can be done by using ANN effectively. The study demonstrates that the Artificial Neural Networks techniques are effective in Application of this technique will contribute significantly to the concrete quality assurance.
Prediction of splitting tensile strength of high strength fiber reinforced self compacting concrete using artificial neural networks
Chowdary, Mohan Lal (author) / Badry, Pallavi (editor) / Narayanasamy, Sudharsan (editor)
PROCEEDINGS OF INTERNATIONAL CONFERENCE ON ADVANCEMENTS IN CONSTRUCTION MATERIALS (ICACM2023) ; 2023 ; Hyderabad, India
AIP Conference Proceedings ; 3146
2024-07-22
7 pages
Conference paper
Electronic Resource
English
Prediction of self-compacting concrete strength using artificial neural networks
| Taylor & Francis Verlag | 2016
Splitting tensile strength and modulus of elasticity of self-compacting concrete
| Online Contents | 2011
Splitting tensile strength and modulus of elasticity of self-compacting concrete
| British Library Online Contents | 2011