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 ANN is of a multilayer… More >

Abdulkadir Karaci^1,*, Hasbi Yaprak², Osman Ozkaraca³, Ilhami Demir⁴, Osman Simsek⁵

CMES-Computer Modeling in Engineering & Sciences, Vol.118, No.1, pp. 207-228, 2019, DOI:10.31614/cmes.2019.04216

Abstract In this study, deep-neural-network (DNN)- and artificial-neural-network (ANN)-based models along with regression models have been developed to estimate the pressure, bending and elongation values of ground-brick (GB)-added mortar samples. This study is aimed at utilizing GB as a mineral additive in concrete in the ratios 0.0%, 2.5%, 5.0%, 7.5%, 10.0%, 12.5% and 15.0%. In this study, 756 mortar samples were produced for 84 different series and were cured in tap water (W), 5% sodium sulphate solution (SS5) and 5% ammonium nitrate solution (AN5) for 7 days, 28 days, 90 days and 180 days. The developed DNN models have three inputs… More >

Mena E. Tawfik^{1, 2}, Peter L. Bishay^{3, *}, Edward A. Sadek¹

CMES-Computer Modeling in Engineering & Sciences, Vol.115, No.1, pp. 105-129, 2018, DOI:10.3970/cmes.2018.115.105

Abstract Monte Carlo Simulations (MCS), commonly used for reliability analysis, require a large amount of data points to obtain acceptable accuracy, even if the Subset Simulation with Importance Sampling (SS/IS) methods are used. The Second Order Reliability Method (SORM) has proved to be an excellent rapid tool in the stochastic analysis of laminated composite structures, when compared to the slower MCS techniques. However, SORM requires differentiating the performance function with respect to each of the random variables involved in the simulation. The most suitable approach to do this is to use a symbolic solver, which renders the simulations very slow, although… 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. Then, four distinct ANNs are… More >

S. Noroozi¹, P. Sewell¹, J. Vinney¹

CMES-Computer Modeling in Engineering & Sciences, Vol.14, No.3, pp. 171-180, 2006, DOI:10.3970/cmes.2006.014.171

Abstract A method that combines a modified back propagation Artificial Neural Network (ANN) and Boundary Element Analysis (BEA) was introduced and discussed in the author's previous papers. This paper discusses the development of an automated inverse boundary element problem engine. This inverse problem engine can be applied to both potential and elastostatic problems.
In this study, BEA solutions of a two-dimensional potential problem is utilised to test the system and to train a back propagation Artificial Neural Network (ANN). Once training is completed and the transfer function is created, the solution to any subsequent or new problems can be obtained… 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 bundle hierarchy and investigate the… 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 elastic modulus and the plastic… More >

Tienfuan Kerh^1,2, J.S. Lai¹, D. Gunaratnam², R. Saunders²

CMES-Computer Modeling in Engineering & Sciences, Vol.26, No.1, pp. 1-12, 2008, DOI:10.3970/cmes.2008.026.001

Abstract Taiwan frequently suffers from strong ground motion, and the current building code is essentially based on two seismic zones, A and B. The design value of horizontal acceleration for zone A is 0.33g, and the value for zone B is 0.23g. To check the suitability of these values, a series of actual earthquake records are considered for evaluating peak ground acceleration (PGA) for each of the zones by using neural network models. The input parameters are magnitude, epicenter distance, and focal depth for each of the checking stations, and the peak ground acceleration is calculated as the output with the… More >

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 optimization algorithm have remarkable potential… 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 to further improve the forecast… More >