Compressive Strength Prediction of High-Strength Concrete Using Regression and ANN Models

Mandal, S.; Shilpa, M.; Rajeshwari, Ramachandra

doi:10.1007/978-981-13-3317-0_41

Cited by 6 publications

(6 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Each input represents the output of a diferent neuron. Te inputs used to solve the problem are multiplied by appropriate weights, and these weighted inputs are summed with the bias value [53]. Te input sums are processed in hidden layers using transfer functions such as linear, tan-sigmoid, and log-sigmoid [112].…”

Section: Artificial Neural Networkmentioning

confidence: 99%

See 1 more Smart Citation

Evaluating 28-Days Performance of Rice Husk Ash Green Concrete under Compression Gleaned from Neural Networks

Singh

Arora

Kumar

et al. 2023

Advances in Materials Science and Engineering

View full text Add to dashboard Cite

Cement manufacturing and utilization is one of the majorly responsible factors for global CO2 emissions. In light of sustainability and climate change concerns, it is essential to find alternative solutions to reduce the carbon footprint of cement. Secondary cementitious materials (SCMs) are helpful in reducing carbon emissions from concrete. One such solution is the use of agricultural waste as SCMs to reduce carbon emissions from concrete. Especially rice husk ash (RHA) is a silica-rich, globally available agricultural waste material. The compressive strength (CS) of concrete is important and is used to evaluate the material’s strength and durability. Predicting CS using a laboratory method is a costly, time-consuming, and complex process. ML-based prediction models are the modern solution to these problems. In this study, a total of 407 datasets are used to develop an ML-based model by using the ANN algorithm to predict the CS of concrete containing RHA. Cement, coarse aggregates, fine aggregates, water, rice husk ash, superplasticizer, and type of sample are used as input parameters to predict CS at 28 days. Various statistical parameters including correlation coefficient (R), root means square error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), Nash-Sutcliffe (NS), and the a20-index have been used to assess the performance of the developed ANN model. The R and RMSE values of training, validation, and testing samples are 0.9928, 0.9864, and 0.9545, and 1.6471 MPa, 2.7149 MPa, and 4.4334 MPa, respectively. The results obtained from this study have been found to be promising and enrich the available literature. This work will nudge civil engineering and material science researchers toward opting for sustainable computing techniques. However, the study’s limitations include the need for additional research into the material’s long-term behaviour as well as the consideration of other characteristics that may affect its strength, such as environmental conditions like temperature and humidity.

show abstract

Section: Artificial Neural Networkmentioning

confidence: 99%

“…Information processed by the transfer function is sent along the output layer as the desired result. A structure in which neurons are arranged in layers and a pattern of connections exists between neurons in each layer is called network architecture [53]. Figure 6 shows the structure of an artifcial neuron model.…”

Section: Artificial Neural Networkmentioning

confidence: 99%

Evaluating 28-Days Performance of Rice Husk Ash Green Concrete under Compression Gleaned from Neural Networks

Singh

Arora

Kumar

et al. 2023

Advances in Materials Science and Engineering

View full text Add to dashboard Cite

show abstract

“…A total of 106 data‐points were used in this study, out of which 75 data‐points were used for training and 31 for testing. The value of R 2 for training and test data sets were 0.9589 and 0.9503, respectively 57 . In another trial, a four‐layer ANN model was built to predict the compressive strength and slump of high strength concrete.…”

Section: Prediction Modelsmentioning

confidence: 99%

Prediction of compressive strength of geopolymer concrete using machine learning techniques

Gupta

Rao

2021

Structural Concrete

View full text Add to dashboard Cite

Geopolymer concrete (GPC) is the result of an inorganic polymerization reaction that takes place in presence of an alkaline medium in the materials such as fly ash and slag, which are rich in silicates and aluminates. In this study, an artificial neural network (ANN), multiple linear regression, and the multivariate nonlinear regression (MNLR) models were designed to predict the 28 days compressive strength of the GPC. To train the models, a total of 289 data sets were used, which were published by different researchers in the open literature. The input parameters, namely, binder content, amount of slag, rest period, curing temperature, curing period, the ratio of NaOH/Na2SiO3, amount of superplasticizer, extra water added, the molarity of NaOH, alkaline activator to binder ratio, amount of coarse, and fine aggregate were used. The performance of the ANN model was better than the multi linear regression (MLR) and multi non‐linear regression (MNLR) models to estimate the strength. The sensitivity analysis on ANN was also performed to study the influence of each parameter. The sensitivity analysis shows that the ratio of NaOH/Na2SiO3 significantly affects the compressive strength of GPC.

show abstract

“…The determination of the compressive strength of high-strength concrete by experimental techniques was a costly and time-consuming operation, and slight errors resulted in the labour being repeated. Hence, different approaches were utilized to address these drawbacks [26]. Taguchi L16 orthogonal array experimental design optimized concrete's mechanical characteristics.…”

Section: Introductionmentioning

confidence: 99%

Experimental and Analytical Study of High-Strength Concrete Containing Natural Zeolite and Additives

Iswarya

Beulah

2022

Civ Eng J

View full text Add to dashboard Cite

The study compares the durability of Natural Zeolite with Metakaolin, Silica Fume, and Fly Ash on high-strength concrete. 300 concrete specimens were tested for compressive strength before and after an acid attack, modulus of elasticity, water absorption, and rapid chloride permeability. 5%, 10%, and 15% of the cement were replaced with cementitious elements while maintaining the same quantity of Natural Zeolite. In this investigation, the water-cement ratio was maintained at 0.35. After 28 days, the specimens were tested for durability. Samples of all mixes were TG/DT and FTIR tested. The optimal percentages of cementitious materials that resulted to the maximum durability enhancements were reported as the study results. Experimental results showed that Natural Zeolite and Metakaolin strengthened the durability of concrete. All the data show that 5% Natural Zeolite with 10% Metakaolin performs well. Good R2values and appropriate independent variable coefficients suggested that the regression findings for high-strength concrete durability were accurate. The P values of all models were less than 0.005 and the F values were statistically significant and appropriate; therefore, the generated models predict concrete's strength with authenticity. Doi: 10.28991/CEJ-2022-08-10-019 Full Text: PDF

show abstract

Compressive Strength Prediction of High-Strength Concrete Using Regression and ANN Models

Cited by 6 publications

References 19 publications

Evaluating 28-Days Performance of Rice Husk Ash Green Concrete under Compression Gleaned from Neural Networks

Evaluating 28-Days Performance of Rice Husk Ash Green Concrete under Compression Gleaned from Neural Networks

Prediction of compressive strength of geopolymer concrete using machine learning techniques

Experimental and Analytical Study of High-Strength Concrete Containing Natural Zeolite and Additives

Contact Info

Product

Resources

About