S.A. Yıldızel^1,2, A.U. Öztürk¹

CMC-Computers, Materials & Continua, Vol.52, No.1, pp. 41-52, 2016, DOI:10.3970/cmc.2016.052.041

Abstract In this study, artificial neural networks trained with swarm based artificial bee colony optimization algorithm was implemented for prediction of the modulus of rapture values of the fabricated glass fiber reinforced concrete panels. For the application of the ANN models, 143 different four-point bending test results of glass fiber reinforced concrete mixes with the varied parameters of temperature, fiber content and slump values were introduced the artificial bee colony optimization and conventional back propagation algorithms. Training and the testing results of the corresponding models showed that artificial neural networks trained with the artificial bee colony More >

Foad Nazari¹, Mohammad Hossein Abolbashari^1,2, Seyed Mahmoud Hosseini³

CMES-Computer Modeling in Engineering & Sciences, Vol.105, No.4, pp. 271-299, 2015, DOI:10.3970/cmes.2015.105.271

Abstract Present study is concerned with three dimensional natural frequency analysis of functionally graded sandwich rectangular plates using Meshless Local Petrov-Galerkin (MLPG) method and Artificial Neural Networks (ANNs).The plate consists of two homogeneous face sheets and a power-law FGM core. Natural frequencies of the plate are obtained by 3D MLPG method and are verified with available references. Convergence study of the first four natural frequencies for different node numbers is the next step. Also, effects of two parameters of “FG core to plate thickness ratio” and “volume fraction index” on natural frequencies of plate are investigated. 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 >

K. Kakuda¹, Y. Hayashi¹, J. Toyotani¹

CMES-Computer Modeling in Engineering & Sciences, Vol.103, No.4, pp. 229-249, 2014, DOI:10.3970/cmes.2014.103.229

Abstract In this paper, we present the application of the particle-based simulations to complicated fluid flow problem with free surfaces. The particle approach is based on the MPS (Moving Particle Simulation) method using hyperbolic-type weighting function to stabilize the spurious oscillatory solutions for solving the Poisson equation with respect to the pressure fields. The hyperbolic-type weighting function is constructed by differentiating the characteristic function based on neural network framework. The weighting function proposed herein is collaterally applied to the kernel function in the SPH-framework. Numerical results demonstrate the workability and validity of the present MPS approach More >

He Xufei¹, Deng Zhongmin², Song Zhitao¹

Structural Durability & Health Monitoring, Vol.8, No.3, pp. 193-208, 2012, DOI:10.32604/sdhm.2012.008.193

Abstract This paper describes an information optimizing scheme which is developed by integrating rough set and hierarchical data fusion. The novel structural damage indices are extracted using the information from different sources and then imported into probabilistic neural network (PNN) for classification and health assessment. In order to enhance the accuracy of diagnosis, results from separate PNN classification are fused to achieve comprehensive decision. Rough set is employed to decrease the spatial dimension of data. The predictive accuracy of optimizing scheme is demonstrated on a helicopter, taken as an example, with varied sensors, for multiple damage More >

Igor Grešovnik^1,2, Tadej Kodelja¹, Robert Vertnik^2,3, Bojan Senčič^3,2,3, Božidar Šarler^1,2,4

CMC-Computers, Materials & Continua, Vol.30, No.1, pp. 19-38, 2012, DOI:10.3970/cmc.2012.030.019

Abstract Artificial neural networks (ANNs) are employed as an alternative to physical modeling for calculation of the relations between the production path process parameters (melting of scrap steel and alloying, continuous casting, hydrogen removal, reheating, rolling, and cooling on a cooling bed) and the final product mechanical properties (elongation, tensile strength, yield stress, hardness after rolling, necking) of steel semi products. They provide a much faster technique of response evaluation complementary to physical modeling. The Štore Steel company process path for production of steel bars is used as an example for demonstrating the approach. The applied… More >

W. Brocks¹, I. Scheider²

Structural Durability & Health Monitoring, Vol.6, No.3&4, pp. 189-212, 2010, DOI:10.3970/sdhm.2010.006.189

Abstract Material parameters are adjustable coefficients in constitutive equations of the mechanical behaviour. Their identification requires a combined experimental and numerical approach, which results in a generally ill-posed inverse problem. Methods commonly applied in computational mechanics like optimisation and neural networks are addressed, and problems like sensitivity, uniqueness and stability are discussed. The cohesive model for describing ductile tearing is chosen as practical example to substantiate the general considerations. More >

D.P. Boso¹, M. Lefik²

CMES-Computer Modeling in Engineering & Sciences, Vol.55, No.3, pp. 319-338, 2010, DOI:10.3970/cmes.2010.055.319

Abstract In this paper we study numerically the mechanical behaviour of wire ropes, particularly the influence of the geometrical configuration on the overall stiffness of the cables. Modelling the behaviour of a cable is a difficult problem, given the complexity of the geometrical layout, contact phenomena occurring among wires and possible yielding of the material. For this reason we pursue a "hierarchical beam approach", to substitute recursively, at each cabling stage, the bundle of wires with an equivalent single strand, having the characteristics computed from the previous level. We consider the first two levels of the… More >

V. Srinivas¹, Saptarshi Sasmal¹, K. Ramanjaneyulu²

Structural Durability & Health Monitoring, Vol.5, No.2, pp. 133-160, 2009, DOI:10.3970/sdhm.2009.005.133

Abstract Many advances have taken place in the area of structural damage detection and localization using several approaches. Availability of cost-effective computing memory and speed, improvement in sensor technology including remotely monitored sensors, advancements in the finite element method, adaptation of modal testing and development of non-linear system identification methods bring out immense technical advancements that have contributed to the advancement of modal-based damage detection methods. Advances in modal-based damage detection methods over the last 20-30 years have produced new techniques for examining vibration data for identification of structural damage. In this paper, studies carried out… More >

D. S. Liu¹, C.Y. Tsai¹

CMES-Computer Modeling in Engineering & Sciences, Vol.39, No.1, pp. 29-48, 2009, DOI:10.3970/cmes.2009.039.029

Abstract Utilizing a thin copper substrate for illustration purposes, this study presents a novel numerical method for extracting the thermo-mechanical properties of a thin-film. In the proposed approach, molecular dynamics (MD) simulations are performed to establish the load-displacement response of a thin copper substrate nanoindented at temperatures ranging from 300~1400 K. The load data are then input to an artificial neural network (ANN), trained using a finite element model (FEM), in order to extract the material constants of the copper substrate. The material constants are then used to construct the corresponding stress-strain curve, from which the… More >