Doo Kie Kim¹, Dong Hyawn Kim², Seong Kyu Chang¹, Sang Kil Chang¹

The International Conference on Computational & Experimental Engineering and Sciences, Vol.2, No.2, pp. 35-40, 2007, DOI:10.3970/icces.2007.002.035

Abstract The stability numbers determining the Armor units are very important to design breakwaters, because armor units are designed for defending breakwaters from repeated wave loads. This study presents a probabilistic neural network (PNN) for predicting the stability number of armor blocks of breakwaters. PNN used the experimental data of van der Meer as train and test data. The estimated results of PNN were compared with those of empirical formula and previous artificial neural network (ANN) model. The comparison results showed the efficiency of the proposed method in the prediction of the stability numbers in spite More >

Doo Kie Kim¹, Seong Kyu Chang¹, Sang Kil Chang¹

The International Conference on Computational & Experimental Engineering and Sciences, Vol.2, No.1, pp. 29-34, 2007, DOI:10.3970/icces.2007.002.029

Abstract Accurate and realistic strength estimation before the placement of concrete is highly desirable. In this study, the advanced probabilistic neural network (APNN) was proposed to reflect the global probability density function by summing the heterogeneous local probability density function automatically determined in the individual standard deviation of variables. Currently, the estimation of the compressive strength of concrete is performed by a probabilistic neural network (PNN) on the basis of concrete mix proportions, and the PNN is improved by the iteration method. However, an empirical method has been incorporated to specify the smoothing parameter in the More >

Atsuya Oishi¹, Shinobu Yoshimura²

CMES-Computer Modeling in Engineering & Sciences, Vol.21, No.2, pp. 93-104, 2007, DOI:10.3970/cmes.2007.021.093

Abstract This paper describes a new local contact search method using a multi-layer neural network and its application to smoothed contact surface consisting of Gregory patches. A contact search process consists of two phases: a global search phase for finding the nearest node-segment pair and a local search phase for finding an exact local coordinate of the contact point within the segment. In the present method, the multi-layer neural network is utilized in the latter phase. The fundamental formulation of the proposed local contact search method is described in detail, and it is applied to smoothed More >

Ramana M. Pidaparti^1,2, Evan J. Neblett²

CMC-Computers, Materials & Continua, Vol.5, No.1, pp. 1-10, 2007, DOI:10.3970/cmc.2007.005.001

Abstract A neural network (NN) model is developed for the analysis and prediction of the mapping between degradation of chemical elements and electrochemical parameters during the corrosion process. The input parameters to the neural network model are alloy composition, electrochemical parameters, and corrosion time. The output parameters are the degradation of chemical elements in AA 2024-T3 material. The NN is trained with the data obtained from Energy Dispersive X-ray Spectrometry (EDS) on corroded specimens. A very good performance of the neural network is achieved after training and validation with the experimental data. After validating the NN More >

E. Abhilash¹, M.A. Joseph¹, Prasad Krishna¹

FDMP-Fluid Dynamics & Materials Processing, Vol.2, No.3, pp. 211-220, 2006, DOI:10.3970/fdmp.2006.002.211

Abstract Aluminium-Silicon alloys are in high de-mand as an engineering material for automotive,aerospace and other engineering applications. Mechanical properties of Al-Si alloys depend not only on chemical composition but also more importantly on microstructural features such as dendritic alpha-aluminiumphase and eutectic silicon particles. As an additive to Al-Si alloys, sodium improves mechanical properties byforming finer and fewer needles like microstructures.Thus, prediction of the macro and microstructures obtained at the end of the solidification is of great interest for the manufacturer of aluminium alloys. Neuralnetworks are sophisticated nonlinear regression routinesthat, when properly “trained”, allow for the identificationof 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… More >

X. Han^1,2,3, G. R. Liu^1,2, G. Y. Li ¹

CMC-Computers, Materials & Continua, Vol.1, No.1, pp. 39-50, 2004, DOI:10.3970/cmc.2004.001.039

Abstract An efficient hybrid numerical method is presented for investigating transient response of cross-ply laminated axisymmetric cylinders subjected to an impact load. In this hybrid numerical method, the laminated cylinder is divided into layered cylindrical elements in the thickness direction. The Hamilton principle is used to develop governing equations of the structure. The displacement response is determined by employing the Fourier transformations and the modal analysis. Numerical examples for analyzing transient waves have been provided in axisymmetric laminated cylindrical structures, both for thin cylindrical shells and thick cylinders.
A computational inverse technique is also presented for More >

D. P. Ghosh¹, S. Gopalakrishnan²

CMC-Computers, Materials & Continua, Vol.1, No.3, pp. 213-228, 2004, DOI:10.3970/cmc.2004.001.213

Abstract Anhysteretic, coupled, linear and nonlinear constitutive relationship for magnetostrictive material is studied in this paper. Constitutive relationships of magnetostrictive material are represented through two equations, one for actuation and other for sensing, both of which are coupled through magneto-mechanical coefficient. Coupled model is studied without assuming any explicit direct relationship with magnetic field. In linear-coupled model, which is assumed to preserve the magnetic flux line continuity, the elastic modulus, the permeability and magneto-elastic constant are assumed as constant. In nonlinear-coupled model, the nonlinearity is decoupled and solved separately for the magnetic domain and mechanical domain More >