Open Access

ARTICLE

Prediction of Fracture Parameters of High Strength and Ultra-High Strength Concrete Beams using Minimax Probability Machine Regression and Extreme Learning Machine

by Vishal Shreyans Shah¹, Henyl Rakesh Shah², Pijush Samui³, A. Ramach,ra Murthy⁴

1 Undergraduate Student, School of Mechanical and Building Sciences (SMBS), VIT University Vellore-632014, Tamil Nadu. E-mail: vs1993shah@gmail.com
2 Undergraduate Student, School of Mechanical and Building Sciences (SMBS), VIT University Vellore-632014, Tamil Nadu. E-mail: henyl_1993@yahoo.com
3 Professor& Director, Centre for Disaster Mitigation and Management (CDMM), VIT University Vellore-632014, Tamil Nadu. E-mail: pijush.phd@gmail.com
4 Senior Scientist, CSIR-Structural Engineering Research Centre, Taramani, Chennai. E-mail:murthyarc@serc.res.in

Computers, Materials & Continua 2014, 44(2), 73-84. https://doi.org/10.3970/cmc.2014.044.073

Abstract

This paper deals with the development of models for prediction of facture parameters, namely, fracture energy and ultimate load of high strength and ultra high strength concrete based on Minimax Probability Machine Regression (MPMR) and Extreme Learning Machine (ELM). MPMR is developed based on Minimax Probability Machine Classification (MPMC). ELM is the modified version of Single Hidden Layer Feed Foreword Network (SLFN). MPMR and ELM has been used as regression techniques. Mathematical models have been developed in the form of relation between several input variables such as beam dimensions, water cement ratio, compressive strength, split tensile strength, notch depth, and modulus of elasticity and output is fracture energy and ultimate load A total of 87 data sets (input-output pairs) are used, 61 of which are used to train the model and 26 are used to test the models. The data-sets used in this study are derived from experimental results. A comparative study has been presented between the developed MPMR and ELM models. The results showed that the developed models give reasonable performance for prediction of fracture energy and ultimate load.

---

Keywords

---