The geneticalgorithm (GA) optimization technique is applied to the optimization of a profiled corrugated horn, designed as a feed for a space-borne remote sensing reflector-antenna system. In addition to using the st...
详细信息
The geneticalgorithm (GA) optimization technique is applied to the optimization of a profiled corrugated horn, designed as a feed for a space-borne remote sensing reflector-antenna system. In addition to using the standard GA (SGA) optimization technique, a profiled corrugated horn is also designed and analyzed using micro GA (muGA). A comparative study has been performed among the various designs. (C) 2002 Wiley Periodicals, Inc.
A new force field was developed using geneticalgorithms (GAs) to optimize molecular mechanics (MM) parameters. The GA-MM approach was applied to the study of technetium (Tc) complexes with coordination numbers of 5 o...
详细信息
A new force field was developed using geneticalgorithms (GAs) to optimize molecular mechanics (MM) parameters. The GA-MM approach was applied to the study of technetium (Tc) complexes with coordination numbers of 5 or 6 and formal oxidation states of + 3 to + 6 on the metal. Both soft and hard donor ligands, coordinated through dative, single, and multiple bonds to Tc, were studied. The new GA-MM force field was tested for the prediction of metric parameters (bond lengths, bond angles and dihedral angles) and overall geometry in reference to X-ray crystallographic data. Despite the chemical diversity found in technetium coordination chemistry, good modeling was achieved in a fraction of the time of higher-level, quantum-based methods, with considerably less computational resources. The GA-MM approach is general enough to be applicable to other d-block metals. (C) 2000 Elsevier Science S.A. All rights reserved.
Artificial neural networks, particularly backpropagation neural network (BPNN), have recently been applied to model various plasma processes. Developing BPNN model, however, is complicated by the presence of several a...
详细信息
Artificial neural networks, particularly backpropagation neural network (BPNN), have recently been applied to model various plasma processes. Developing BPNN model, however, is complicated by the presence of several adjustable factors whose optimal values are initially unknown. These may include initial weight distribution, hidden neurons, gradient of neuron activation function, and training tolerance. A methodology is presented to optimize various factor effects, which was accomplished hy implementing geneticalgorithm (Gh) on the best models. Particular emphasis was placed on a qualitative measure of initial weight distribution, whose magnitude and directionality were varied. Interactions between factors were examined by means of a 2(4) factorial experiment. Parametric effect analysis revealed the dissimilarity between the best and average prediction characteristics. Both gradient and initial weight distribution exerted a conflicting effect on both average and best performances. GA-optimized models exhibited about 20% improvement over the experimentally chosen best models. Further improvement of more than 30% was achieved with respect to statistical response surface models. Plasma modeled is an inductively coupled plasma, whose experimental data were collected with Langmuir probe from an etch equipment capable of processing 200-mm wafers. (C) 2001 Published by Elsevier Science B.V.
暂无评论