• Journal of the Society of Naval Architects of Korea
• /
• v.34 no.1
• /
• pp.122-129
• /
• 1997

Thermo-elastic-plastic analyses used in solving plate forming process are often computationally expensive. To obtain an optimal process of line heating typically requires numerous iterations between the simulation and a finite element analysis. This process often becomes prohibitive due to the amount of computer time required for numerical simulation of line heating process. Therefore, a new techniques that could significantly reduce the computer time required to solve a complex analysis problem would be beneficial. In this paper, we considered factors that influence the bending effect by line heating and developed inference engine by using the concept of artificial neural network. To verify the validity of the neural network, we used results obtained from numerical analysis. We trained the neural network with the data made from numerical analysis and experiments varying the structure of neural network, in other words varying the number of hidden layers and the number of neurons in each hidden layers. From that we concluded that if the number of neurons in each hidden layers is large enough neural network having two hidden layers can be trained easily and errors between exact value and results obtained from trained network are not so large. Consequently, if there are enough number of training pairs, artificial neural network can infer similar results. Based on the numerical results, we applied the artificial neural network technique to deal with mechanical behavior of line heating at simulation stage effectively.

• Journal of the Korean Magnetics Society
• /
• v.12 no.5
• /
• pp.184-188
• /
• 2002

The Cu/Ni/Cu(002)/Si(100) films which have perpendicular magnetic anisotropy were deposited by e-beam evaporation methods. From the reflection high energy electron diffraction pattern, the films were confirmed to be grown epitaxially on silicon. After 2X lots ions/$\textrm{cm}^2$ C+ irradiation, magnetic easy-axis was changed from surface normal to in-plane as shown in the hysteresis loop of magneto-optical Kerr effects. It became manifest from analysis of X-ray reflectivity and grazing incident X-ray diffraction that even though interface between top Cu layer and Ni layer became rougher, the contrast of Cu and Ni's electron density became manifest after ion irradiation. In addition, the strain after deposition of the films was relaxed after ion irradiation. Strain relaxation related with change of magnetic properties and mechanism of intermixed layer's formation was explained by thermo-chemical driving force due to elastic and inelastic collision of ions.