G. Jayaprakash¹, M. P. Muthuraj^2,*

CMC-Computers, Materials & Continua, Vol.54, No.1, pp. 83-102, 2018, DOI:10.3970/cmc.2018.054.083

Abstract This paper discusses the applicability of relevance vector machine (RVM) based regression to predict the compressive strength of various self compacting concrete (SCC) mixes. Compressive strength data various SCC mixes has been consolidated by considering the effect of water cement ratio, water binder ratio and steel fibres. Relevance vector machine (RVM) is a machine learning technique that uses Bayesian inference to obtain parsimonious solutions for regression and classification. The RVM has an identical functional form to the support vector machine, but provides probabilistic classification and regression. RVM is based on a Bayesian formulation of a More >

Susom Dutta¹, A. Ramach,ra Murthy², Dookie Kim³, Pijush Samui⁴

CMC-Computers, Materials & Continua, Vol.53, No.2, pp. 157-174, 2017, DOI:10.3970/cmc.2017.053.167

Abstract In the present scenario, computational modeling has gained much importance for the prediction of the properties of concrete. This paper depicts that how computational intelligence can be applied for the prediction of compressive strength of Self Compacting Concrete (SCC). Three models, namely, Extreme Learning Machine (ELM), Adaptive Neuro Fuzzy Inference System (ANFIS) and Multi Adaptive Regression Spline (MARS) have been employed in the present study for the prediction of compressive strength of self compacting concrete. The contents of cement (c), sand (s), coarse aggregate (a), fly ash (f), water/powder (w/p) ratio and superplasticizer (sp) dosage More >

G. Smith¹, E. Schlangen², P.E.J. Flewitt³, A.G. Crocker⁴, A. Hodgkins⁵

CMC-Computers, Materials & Continua, Vol.51, No.3, pp. 163-185, 2016, DOI:10.3970/cmc.2016.051.163

Abstract Two linked models have been developed to explore the relationship between the amount of porosity arising in service from both radiolytic oxidation and fast neutron damage that influences both the strength and the force-displacement (load-displacement) behaviour and crack propagation in pile grade A graphite used as a nuclear reactor moderator material. Firstly models of the microstructure of the porous graphite for both unirradiated and irradiated graphite are created. These form the input for the second stage, simulating fracture in lattice-type finite element models, which predicts force (load)-displacement and crack propagation paths. Microstructures comprising aligned filler More >

Smitha Gopinath^1,2, S. Meenu³, A. Ramach,ra Murthy¹

CMC-Computers, Materials & Continua, Vol.51, No.2, pp. 81-103, 2016, DOI:10.3970/cmc.2016.051.081

Abstract This paper presents experimental and analytical investigations on concrete beams reinforced with basalt fiber reinforced polymer (BFRP) and steel fibers without stirrups. Independent behaviour of BFRP reinforced beams and steel fiber reinforced beams were evaluated and the effect of combining BFRP bars and steel fiber was investigated in detail. It is found that combining steel fibers with BFRP could change the shear failure of BFRP reinforced beam to flexural failure. Further, the existing analytical models were reviewed and compared to predict the shear strength of both FRP reinforced and steel fiber reinforced beams. Based on More >

Q.W. Yang¹, S.G. Du^1,2

CMC-Computers, Materials & Continua, Vol.47, No.3, pp. 217-236, 2015, DOI:10.3970/cmc.2015.047.217

Abstract Size effect is a major issue in concrete structures and occurs in concrete in any loading conditions. In this study, size effect on concrete cubic compressive strength is modeled with a back-propagation neural network. The main advantage in using an artificial neural network (ANN) technique is that the network is built directly from experimental data without any simplifying assumptions via the self-organizing capabilities of the neural network. The proposed ANN model is verified by using 27 experimental data sets collected from the literature. For the large specimens, a modified ANN is developed in the paper More >

N. Ma^1,2, K. Sato³, K. Takada⁴

CMC-Computers, Materials & Continua, Vol.46, No.3, pp. 195-219, 2015, DOI:10.3970/cmc.2015.046.195

Abstract The local mechanical behaviors of advanced high strength steels undergoing a very large strain from uniform plastic deformation to fracture were investigated with the aid of a measured displacement field and a measurement based FEM. As a measurement method, a digital image grid method (DIGM) was developed and the three-direction transient displacement field on uniaxial tensile test pieces was measured. Combining the measured transient displacement field with the finite element method, a measurement based FEM (M-FEM) was developed for the computation of distribution of the local strains, local stresses and ductile damage accumulation in a More >

Vishal Shreyans Shah¹, Henyl Rakesh Shah², Pijush Samui³, A. Ramachra Murthy⁴

CMC-Computers, Materials & Continua, Vol.44, No.2, pp. 73-84, 2014, DOI: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 More >

Y. T. Wu¹, J. Z. Cui², Y. F. Nie³, Y. Zhang³

CMC-Computers, Materials & Continua, Vol.42, No.3, pp. 205-226, 2014, DOI:10.3970/cmc.2014.042.205

Abstract Core–shell particle–filled PA6/EPDM–g–MA/HDPE ternary blend has excellent mechanical properties. In this paper, effective elastic properties and tensile yield strength of the ternary blend are predicted by the second–order two– scale method, to investigate the relationship between morphology and mechanical properties. The method and the limit analysis for predicting mechanical properties of random heterogeneous materials are briefly introduced. Realistic morphology of the ternary blend including both core–shell particles and pure particles is simulated, and finite element mesh is generated. The unified strength theory is embedded in the method for the convenience of selecting a suitable yield More >

Yuvaraj P¹, A Ramachra Murthy², Nagesh R Iyer³, S.K. Sekar⁴, Pijush Samui⁵

CMC-Computers, Materials & Continua, Vol.41, No.3, pp. 193-214, 2014, DOI:10.3970/cmc.2014.041.193

Abstract This paper presents fracture mechanics based Artificial Neural Network (ANN) model to predict the fracture characteristics of high strength and ultra high strength concrete beams. Fracture characteristics include fracture energy (Gf), critical stress intensity factor (KIC) and critical crack tip opening displacement (CTODc). Failure load of the beam (Pmax) is also predicated by using ANN model. Characterization of mix and testing of beams of high strength and ultra strength concrete have been described. Methodologies for evaluation of fracture energy, critical stress intensity factor and critical crack tip opening displacement have been outlined. Back-propagation training technique… More >

Trenton M. Ricks¹, Thomas E. Lacy, Jr.^1,2, Brett A. Bednarcyk³, Steven M.Arnold³, John W. Hutchins¹

CMC-Computers, Materials & Continua, Vol.40, No.2, pp. 99-130, 2014, DOI:10.3970/cmc.2014.040.099

Abstract A multiscale modeling methodology was developed for continuous fiber composites that incorporates a statistical distribution of fiber strengths into coupled multiscale micromechanics/ finite element (FE) analyses. A modified twoparameter Weibull cumulative distribution function, which accounts for the effect of fiber length on the probability of failure, was used to characterize the statistical distribution of fiber strengths. A parametric study using the NASA Micromechanics Analysis Code with the Generalized Method of Cells (MAC/GMC) was performed to assess the effect of variable fiber strengths on local composite failure within a repeating unit cell (RUC) and subsequent global… More >