Mechanical Strength Estimation of Self-Compacting Geopolymer Concrete using ReLU based Deep Neural Network

ABSTRACT

A deep learning artificial neural network model developed in Tensorflow using the ReLU function is presented in this paper to determine the effect of nine different input parameters on the mechanical strength of self-compacting geopolymer concrete (SGC). With the application of the above model, it has been observed that the convergence outcome of our model is predicted with minimum error. The novelty of our model is the ReLU function which improves the accuracy of the results. Our study presents a systematic investigation of the compressive strength, flexural strength, and tensile strengths of SGC depending upon nine vital parameters, such as GFS, Fly ash, NaOH, Na₂SiO₃ content, Age of specimens, Slump Value, T₅₀, L Box and J Ring value as input. A large number of experiments were conducted to prepare a comprehensive database of the mechanical strength of Flyash-GFS-based SGC. The database has a total of 396 samples which were collected from 132 distinct mixtures, where the minimum and maximum compressive strength value is 7.7 Mpa and 66.7 Mpa, respectively. For the prediction based on deep learning, authors have performed an adequate number of iterations for both training and testing using error estimation parameters such as mean absolute error (MAE), mean square error (MSE), and root mean square error (RMSE). The error parameter values for the compressive strength of SGC are 2.42, 2.94 and 1.07, respectively, for MAE, RMSE and MSE. The other mechanical properties and their error parameter have also been thoroughly evaluated in our work.

KEYWORDS:

• Self-compacting geopolymer
• ANN
• ReLU function
• neural network
• Flyash
• slag

Acknowledgements

The authors want to acknowledge the support of laboratory environment and lab assistants of National Institute of technology Silchar, India, during the experimental works.

Disclosure statement

No potential conflict of interest was reported by the author(s).

Data vailability statement

The authors will share all the data related to this manuscript on reasonable request.

Ethics approval and consent to participate

The manuscript is prepared based on the ethical standard.

Consent for publication

Yes

Author contribution

All authors contributed to the study, review, experimental work, empirical work, design and manuscript preparation equally.

Additional information

Funding

The authors declare that no funds, grants, or other support were received during the preparation of this manuscript.