Buy article PDF
The purchased file will be sent to you
via email after the payment is completed.
US$ 35
|
Structural Engineering and Mechanics Volume 95, Number 4, August25 2025 , pages 263-279 DOI: https://doi.org/10.12989/sem.2025.95.4.263 |
|
|
|
Machine learning regression and optimal neural network models for the prediction of compressive strength of high strength SCC-A comparative study |
||
Siddesha Hanumanthappa, D.S Rajendra Prasad, Pavan Kumar Emani and H.D. Sharma
|
||
| Abstract | ||
| This paper attempts to provide an insight into studies of Machine learning regression and Optimal Neural Network models for the prediction of compressive strength of high-strength self-compacting concrete using project site testing results. We use these models, as they are time and cost-effective to gather data and to predict the incident itself, or, more likely, because the incident will occur in some future time. Prediction of Compressive Strength of High Strength Self-Compacting Concrete (HSSCC) for 7 days, 28 days, 56 days, and 90 days based on design mix parameters is implemented in this work by adopting an Optimal Neural Network model. An Information Criterion (AIC) algorithm, along with the golden search algorithm, was applied progressively till the optimal network with a minimum AIC was found. Machine learning Multiple Regression models are also developed to predict compressive strength of concrete from one or more design mix variables. The Regression equations are developed for computing the compressive strength of concrete based on the 9 input design mix parameters. The results of the models were encouraging and found to be reliable. | ||
| Key Words | ||
| compressive strength; concrete; machine learning; optimal neural network; regression learner | ||
| Address | ||
| Siddesha Hanumanthappa, D.S Rajendra Prasad, Pavan Kumar Emani and H.D. Sharma: Department of Civil Engineering, Siddaganga Institute of Technology, B.H. Road, Tumakuru – 572 103, Karnataka, India | ||