This paper proposes intelligent system for dynamic modeling of material properties. Usability of the system is demonstrated by practical examples. The intelligent system is not limited only to the modeling of material properties, but it is a general approach for studying of different systems.

The proposed intelligent system consists of two parts: intelligent modelerand intelligent optimizer. The intelligent modeler is intended for the modeling of the system for which the behavior is not yet known. The intelligent optimizer is used for the optimization of the parameters for the system already described. Each of the two parts has its own input and output. The input to the modeler are the experimental data on the system studied, while the output is the model developed during modeling. The input to the optimizer is the model containing system parameters to be optimized. In most cases the modeler output is in the same time the optimizer input. The output of the optimizer is the optimized set of the system parameters.

The intelligent modeler gathers knowledge about the system studied using on-line sensing equipment. Since new knowledge is continuously coming into the modeler, the data are in fact dynamic environment. Consequently, the system as well as its optimized parameter values slowly change. The optimized parameters change the state of the environment (and vice versa) and influence general behavior of the system studied.

In the proposed concept, evolutionary algorithms are used for both intelligent modeler and intelligent optimizer. The genetic programming and the genetic approximation tools represent the core of the intelligent modeler. The core of the intelligent optimizer is genetic algorithm tool.

The paper concludes with the practical examples where the proposed intelligent system serves as a modeling tool for studying several different systems, i.e., modeling of bending capabilities of material, modeling of impact toughness, modeling of yield stress.

• Legal notice:
  

  Copyright (c) Pielaszek Research, all rights reserved.
  The above materials, including auxiliary resources, are subject to Publisher's copyright and the Author(s) intellectual rights. Without limiting Author(s) rights under respective Copyright Transfer Agreement, no part of the above documents may be reproduced without the express written permission of Pielaszek Research, the Publisher. Express permission from the Author(s) is required to use the above materials for academic purposes, such as lectures or scientific presentations.
  In every case, proper references including Author(s) name(s) and URL of this webpage: https://science24.com/paper/11940 must be provided.