Modeling compressive strength of recycled aggregate concrete by Artificial Neural Network, Model Tree and Non-linear Regression

Deshpande, Neela; Londhe, Shreenivas; Kulkarni, Sushma

doi:10.1016/j.ijsbe.2014.12.002

Cited by 179 publications

(76 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…6, it is noticed that for the test specimens, when RI is increased from 0.47 to 2.35 (for MS fiber % of 0.5 to 2.5 respectively), the CS has increased to 50%, i.e., from 20 …”

Section: Cylinder Compressive Strengthmentioning

confidence: 94%

“…Statistical model is used to predict the effect of changes in the variables to the system, but should be as close as possible to the real system and incorporate most of its salient features [19]. Multiple Regression Analysis will help in establishing a mathematical relationship between two or more independent variables and a dependent variable by fitting a linear equation to observed data; and every value of the independent variable is associated with a value of the dependent variable [20].…”

Section: Predictive Empirical Modelsmentioning

confidence: 99%

“…Deshpande et al [20] have brought out that the compressive strength of concrete can be derived through appropriate statistical regression analysis. While Ramadoss and Nagamani [28] have established the relationship of both flexural and splitting tensile strength at 28 days with fiber reinforcing index (RI) (at a given fiber content) in fiber reinforced concrete, the present authors have found out through thorough review of literature that there are limited studies on the prediction of mechanical strength (compressive, splitting-tensile and flexural strength) of fiber reinforced cementitious matrix (FRCM).…”

Section: Predictive Empirical Modelsmentioning

confidence: 99%

See 2 more Smart Citations

Experimental and Predictive Mechanical Strength of Fiber Reinforced Cementitious Matrix (Frcm)

Sakthivel¹

2014

geomate

View full text Add to dashboard Cite

Fiber Reinforced Cementitious Matrix (FRCM) are sustainable building materials as it uses lesser quantities of natural resources as raw materials for production, when compared to conventional concrete. This study is an attempt to explore the possibility of using crimped mild steel (MS) fibers (12.5 mm length) as reinforcement in cementitious matrix, with sand-cement and water-cement ratio in line with the ACI Codes. From the experimental results, it was found that when the percentage of MS fibers is increased in cement-based mortar from 0.5% to 2.5% of volume of specimens (with 0.5% interval), there is a corresponding increase in the cylinder compressive strength and splitting-tensile strength at 7 and 28 days, and flexural strength at 28 days. There was an increase in compressive strength of 74%, splitting-tensile strength of 38% and flexural strength of 35% at 28 days, when MS fibers of 2.5% was used, when compared to control mortar specimens (with no fibers). Also, the predictive strength models were developed from the experimental data using statistical regression analysis. It was observed that the experimental results of FRCM highly correlate with the predicted values, with minimum prediction error.

show abstract

“…6, it is noticed that for the test specimens, when RI is increased from 0.47 to 2.35 (for MS fiber % of 0.5 to 2.5 respectively), the CS has increased to 50%, i.e., from 20 …”

Section: Cylinder Compressive Strengthmentioning

confidence: 94%

Section: Predictive Empirical Modelsmentioning

confidence: 99%

Section: Predictive Empirical Modelsmentioning

confidence: 99%

See 1 more Smart Citation

Experimental and Predictive Mechanical Strength of Fiber Reinforced Cementitious Matrix (Frcm)

Sakthivel¹

2014

geomate

View full text Add to dashboard Cite

show abstract

“…ANN has been used to predict concrete mix proportions [43] and compressive strength of concrete with different properties, subjected to various tests [25]; [44]- [46] and model the compressive strength of recycled aggregate concrete [47]. The workability of concrete with metakaolin and flyash [48][49], mechanical behavior of concrete at high temperatures [50]; and concrete strength [51][52][53][54] have also been ascertained.…”

Section: Ann Prediction and Modeling Studiesmentioning

confidence: 99%

Modeling and Prediction of Flexural Strength of Hybrid Mesh and Fiber Reinforced Cement-Based Composites Using Artificial Neural Network (Ann)

Sakthivel¹

2016

geomate

View full text Add to dashboard Cite

ABSTRACT:In this paper, Artificial Neural Network (ANN) has been used to predict the equivalent flexural strength of hybrid mesh and fiber reinforced cement-based composites (HMFRCBC). Three ANN models (Models 1, 2 and 3) were developed for predicting the flexural strength of cement-based composites. Model 1 used 48 data of the previously published data of the present authors and Model 2 used 48 data (out of the 75 ANN validated data) from previous studies related to mesh reinforced cement-based composites. Model 3 with 98 data (combined data sets of Model 1 and Model 2) employed seven input parameters, namely the width and depth of slab, cylinder compressive strength, mesh ultimate strength, mesh volume fraction, fiber volume fraction, fiber ultimate strength, and an output, the ultimate flexural strength of mesh and fiber reinforced cement based composites. Hidden layer was fixed based on 5 trial runs for Models 1 and 2, and 10 trial runs for Model 3. All the three models (Models 1, 2 and 3) were trained with 80% of the data, and tested with balance 20% of the data. For Models 1, 2 and 3, the Lowest Individual Error (LIE) of 11.18%, 6.95% and 11.56% (respectively) is achieved in Trial Run No.1.4 (with I-H-O, Input-Hidden Neurons-Output of 5-6-1), Trial Run No.2.2 (5-4-1) and Trial Run No.3.7 (7-10-1) respectively. Also, the lowest absolute average deviation (AAD%) of 4.81%, 3.51% and 4.58% (respectively); lowest Root Mean Square Error (RMSE) of 0.86, 0.76 and 0.99 (respectively); and highest R 2 of 0.933, 0.988 and 0.975 (respectively) are seen for these trials 1.4, 2.2, 3.7 in Models 1, 2 and 3 respectively. All the three ANN models were found to be in good agreement with actual results, and these three ANN models can serve as simple but reliable predictive tools in determination of flexural strength of HMFRCBC.

show abstract

“…Thus to improve knowledge about behaviour of CBT aggregate in concrete, and to reduce the cost and time required for testing, models with behaviour simulation capabilities were investigated using the input and output data from experimental study [3]. One of the modelling techniques that are used for simulating behaviour of concrete containing recycled material are Artificial Neural Networks (ANN), which have over time become an important research tool [4][5][6]. However, an effectiveness and applicability of reported relationships between concrete components and properties still remain questionable.…”

Section: Introductionmentioning

confidence: 99%

Prediction of properties of recycled aggregate concrete

Miličević¹,

Šipoš²

2017

JCE

View full text Add to dashboard Cite

Modeling compressive strength of recycled aggregate concrete by Artificial Neural Network, Model Tree and Non-linear Regression

Cited by 179 publications

References 22 publications

Experimental and Predictive Mechanical Strength of Fiber Reinforced Cementitious Matrix (Frcm)

Experimental and Predictive Mechanical Strength of Fiber Reinforced Cementitious Matrix (Frcm)

Modeling and Prediction of Flexural Strength of Hybrid Mesh and Fiber Reinforced Cement-Based Composites Using Artificial Neural Network (Ann)

Prediction of properties of recycled aggregate concrete

Contact Info

Product

Resources

About