• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.3
• /
• pp.215-222
• /
• 2001

Neural network based models of semiconductor manufacturing processes have been shown to offer advantages in both accuracy and generalization over traditional methods. However, model development is often complicated by the fact that back-propagation neural networks contain several adjustable parameters whose optimal values unknown during training. These include learning rate, momentum, training tolerance, and the number of hidden layer neurOnS. This paper presents an investigation of the use of genetic algorithms (GAs) to determine the optimal neural network parameters for the modeling of plasma-enhanced chemical vapor deposition (PECVD) of silicon dioxide films. To find an optimal parameter set for the neural network PECVD models, a performance index was defined and used in the GA objective function. This index was designed to account for network prediction error as well as training error, with a higher emphasis on reducing prediction error. The results of the genetic search were compared with the results of a similar search using the simplex algorithm.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.37 no.8
• /
• pp.975-981
• /
• 2013

A robust optimization is only one of the ways to minimize the effects of variances in design variables on the objective functions at the preliminary design stage. To predict the variances and to formulate the probabilistic constraints are the most important procedures for the robust optimization formulation. Though several methods such as the process capability index and the six sigma technique were proposed for the prediction and formulation of the variances and probabilistic constraints, respectively, there are few attempts using a percent defective which has been widely applied in the quality control of the manufacturing process for probabilistic constraints. In this study, the robust optimization for a lower control arm of automobile vehicle was carried out, in which the design space showing the mean and variance sensitivity of weight and stress was explored before robust optimization for a lower control arm. The 2nd order Taylor expansion for calculating the standard deviation was used to improve the numerical accuracy for predicting the variances. Simplex algorithm which does not use the gradient information in optimization was used to convert constrained optimization into unconstrained one in robust optimization.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.8 no.8
• /
• pp.1810-1817
• /
• 2004

A diffractive optical element(DOE) for an optical pickup system is proposed in this thesis. Optimization algorithms are used to synthesise the DOE to meet a detailed specification of the two kind of cost function. The one isso called as apodization which refers to the process of suppressing the secondary maxima and the other is so called as sharpness which refers to the process of reducing the size of primary maxima. The result obtained by simplex optimization method is that the apodization and sharpness are well achieved separately. In apodization, the secondary maxima is reduced up to 39%. And in sharpness, the size of first maxima is reduced to 95.2％.

• Korean Chemical Engineering Research
• /
• v.53 no.2
• /
• pp.193-198
• /
• 2015

The high-pressure phase behavior of a polycaprolactone (Mw=56,145 g/mol, polydispersity 1.2), dichloromethane, and carbon dioxide ternary system was measured using a variable-volume view cell. The experimental temperatures and pressures ranged from 313.15 K to 353.15 K and up to 300 bar as functions of the $CO_2$/dichloromethane mass ratio and temperature, at poly(D-lactic acid) weight fractions of 1.0, 2.0, and 3.0%. The correlation results were obtained from the hybrid equation of state (Peng-Robinson equation of state + SAFT equation of state) for the $CO_2$-polymer system using the van der Waals one-fluid mixing rule. The three binary interaction parameters were optimized by the simplex method algorithm.