Current Proceedings on Technology
Yazarlar: Mahboobeh Habibinejad, Mohsen Ramani, Mostafa Khosravi
Konular:-
Anahtar Kelimeler:-
Özet: The development and processing of materials are complex. Although, research activities help a lot (greatly) to understand the fundamental phenomena in materials science, many problems about the quality of materials still remain unclear. The main reason for the lack of the progress in predicting mechanical behaviour of materials is that they depend on a large number of variables. A system identification problem can be formulated as an optimization task where the objective is to find a model and a set of parameters that minimize the prediction error between the plant outputs i.e., the measured data, and the model output. The Genetic Algorithm (GA) is able to generate model structures from input - output measurement of the system, so the GA is potentially useful for system identification. Subsequently, the system parameters are identified by a process formed by blending the GA technique. The aim of this paper is to employ the GA method to predict the gradation of API-X70 steel. We have the goal to find mathematical models, which describe the behaviour of the plant better and very close to reality. The achieved results show that by using the proposed approach, the gradation of steel is predictable with an acceptable error. Keyworks: GA, system identification, gradation of particles, Zener_Hollomon equation, API-X70 steel;