A Design of New Brands of Martenzite Steels by Artificial Neural Networks

Abstract

The paper proposes a model-based approach for the design of martenzite structure steels with improved mechanical and plastic characteristics using proper composition and thermal treatment. For that purpose, artificial neural models approximating the dependence of steels strength characteristics on the percentage content of alloying components were trained. These non-linear models are further used within an optimization gradient procedure based on backpropagation of utility function through neural network structure. In order to optimizing the steel characteristics via its chemical composition, several steel brands with high values of tensile strenght, yield strenght and relative elongation were designed. A steel composition having economical alloying and proper for practical application was determined comparing several obtained decisions. The usage of that steel will lead to lightening of the hardware for automobile industry.

Authors and Affiliations

Yavor LUKARSKI, Sasho POPOV, Nikolay TONCHEV, Petia KOPRINKOVA-HRISTOVA, Silvia POPOVA

Keywords

Related Articles

Corrosion Behavior of Zinc Alloy Layers

The alloying of zinc with some additional elements in specific quantities could be reliably used in the hot-dip coating process. These elements conferr substantially improved performance to the end-product specially by i...

Sculpture, Extended Nature

The paper portrays some aspects that show how nature is implemented into the graphic values domain by confronting the physical image of the artistic subject. The article presents some rules that have marked over time the...

Physico-Mechanical Characteristics of Hard Alloys Made Out of Many Carbides

The Hard alloys of type WC-TiC-Co can be used to process materials with long chips, such as steels [1]. Titanium carbide or TiC-WC solid solutions, added as alloying constituents in the compositions of WC-Co pseudo-alloy...

The Behaviour of Acid Slag in the Tundish

In the tundish, purification of steel is given by the use of an oxide powder on the steel surface. This powder perform several important functions, such as thermal insulation, protection against liquid steel surface oxid...

Modelling by Finite Element Analysis Method of Stress State Establishing for an Steel Alloy

The paper presents some results about the tension state in samples subject to pure bending fatigue process. Numerical simulation based on finite element method was used. The tension field induced by a vertical deformatio...

Download PDF file
  • EP ID EP625966
  • DOI -
  • Views 102
  • Downloads 0

How To Cite

Yavor LUKARSKI, Sasho POPOV, Nikolay TONCHEV, Petia KOPRINKOVA-HRISTOVA, Silvia POPOVA (2011). A Design of New Brands of Martenzite Steels by Artificial Neural Networks. Analele Universitatii "Dunarea de Jos" din Galati. Fascicula IX, Metalurgie si Stiinta Materialelor, 34(3), 10-14. https://europub.co.uk/articles/-A-625966