Application of neural networks in steels' chemical composition design
نویسندگان
چکیده
منابع مشابه
Optimisation of the Chemical Composition and Manufacturing Route for ODS RAF Steels for Fusion Reactor Application
As the upper temperature for use of reduced activation ferritic/martensitic (RAFM) steels is presently limited by a drop in mechanical strength at about 550°C, Europe, Japan and the US are actively researching steels with high strength at higher operating temperatures, mainly using stable oxide dispersion. In addition, the numerous interfaces between matrix and oxide particles are expected to a...
متن کاملEvaluation of Super Clean Steels According to Chemical Composition
Equipment of ŽĎAS, a. s. electric steel plant enables to make commercial high-grade steels with guaranteed high internal purity. Making of super clean steels means essential enhancement in qualitative requirements that requests new technological elements as well as operative management of steel making and treatment process. In order to verify the possibility to make these steels under ŽĎAS, a.s...
متن کاملParallelizing Design of Application Tailored Neural Networks
In a companion paper, a constructive approach for designing feedforward neural networks using genetic algorithms is proposed [7, 8]. The algorithm constructs networks with close to optimum size growing hidden layer units in a problem specific manner and has very good generalization properties. In this paper, in order to make the constructive design algorithm computationally efficient, a two sta...
متن کاملEvolutionary Design of Application Tailored Neural Networks
| First, an evolutionary algorithm for designing a single hidden layer feedfor-ward neural networks is proposed. The algorithm constructs a problem tailored neu-ral network by incremental introduction of new hidden units. Each new hidden unit is added to the network by linear partitioning of the hidden-layer representation through a genetic search. Second, a two stage algorithm speed-up is achi...
متن کاملSEISMIC DESIGN OF DOUBLE LAYER GRIDS BY NEURAL NETWORKS
The main contribution of the present paper is to train efficient neural networks for seismic design of double layer grids subject to multiple-earthquake loading. As the seismic analysis and design of such large scale structures require high computational efforts, employing neural network techniques substantially decreases the computational burden. Square-on-square double layer grids with the va...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Journal of the Brazilian Society of Mechanical Sciences and Engineering
سال: 2003
ISSN: 1678-5878
DOI: 10.1590/s1678-58782003000200012