Wyniki wyszukiwania - BazTech

1

Predicting the microstructure of compacted graphite iron using a fuzzy knowledge‑based system

Gumienny Grzegorz, Macioł Andrzej, Macioł Piotr

Archives of Civil and Mechanical Engineering

|

2023

|

Vol. 23, no. 2

art. no. e87, 2023

EN

One of the important engineering materials is compacted graphite iron (CGI). Obtaining an expected microstructure leading to desired material properties is relatively difficult. In this paper, we present an approach to predicting the microstructure with a fuzzy knowledge-based system. On the basis of the results of statistical analysis and expert knowledge, an original taxonomy of CGI casts was formulated. The procedure of data acquisition, specimen preparation, analysis procedure and microstructures obtained are presented. Methods for expert experience-supported knowledge extraction from experimental data, as well as methods for formalizing knowledge as fuzzy rules, are introduced. The proposed rulesets, the reasoning process, and exemplary results are provided. The verification results showed that, using our approach, it is possible to effectively predict the microstructure and properties of CGI casts even in the absence of sufficient data to use data-driven knowledge acquisition. On the basis of the results obtained, examples of possible applications of the developed approach are presented.

2

Evolution of δ phase precipitates in Inconel 625 superalloy additively manufactured by laser powder bed fusion and its modeling with fuzzy logic

Staroń Sylwia, Macioł Piotr, Dubiel Beata, Gola Kewin, Falkus Jan

Archives of Civil and Mechanical Engineering

|

2023

|

Vol. 23, no. 2

art. no. e86, 2023

EN

Experimental and modeling studies of the evolution of plate-like δ phase precipitates in Inconel 625 superalloy additively manufactured by the laser powder bed fusion process are performed. The maximum Feret diameter and the number of particles per unit area are used as parameters describing the size and distribution of the δ phase precipitates. On the basis of microstructural analysis and quantitative image analysis, the effect of time and temperature on the development of δ phase precipitates is determined. The distinct differences in the intensity of precipitation, growth, and coarsening of the δ phase precipitates during annealing at temperatures of 700 and 800 °C up to 2000 h are shown. The experimental results are compared with computational data obtained by thermodynamic modeling. Using the experimentally determined parameters of the δ phase precipitates in different variants of annealing, a fuzzy logic-based phase distribution model is designed. Since the quantity of available data was too small to train a model with the machine learning approach, expert knowledge is used to design the rules, while numerical data are used for its validation. Designed rules, as well as reasoning methodology are described. The proposed model is validated by comparing it with the experimental results. It can be used to predict the size and number density of the δ phase precipitates in the additively manufactured Inconel 625, subjected to long-term annealing at temperatures of 700-800 °C. Due to limited experimental data, the quality of assurance is not perfect, but warrants preliminary research.

3

Rule-based controlling of a multiscale model of precipitation kinetics

Macioł Piotr

Computer Methods in Materials Science

|

2018

|

Vol. 18, No. 2

64--78

EN

One of the most important obstacles of widening of multiscale modelling is its high computational demand. It is caused by the fact, that each of numerous fine scale models has comparable computational requirements to a coarse scale one. There are several ways of decreasing of computational time of multiscale models. Adaptation of a structure of a model is one of the most promising. In this paper the Adaptive Multiscale Modelling Methodology is described, including Knowledge-Based adaptation of the multiscale model of precipitation kinetics during heat treatment. Core features of the methodology are introduced. The numerical model of heat treatment of an aluminium alloy based on the methodology and the dedicated framework is presented. Besides modelling of macroscopic heat transfer, models of precipitation kinetics based on thermodynamic calculations are included. To decrease computational requirements arising from coupling of the macroscale model and the thermodynamic models, metamodeling and similarity approaches are applied. Computations with several configuration of rules are described, as well as their results. Reliability and time consumption of computations are discussed. Future perspectives of combining of modelling and metamodeling in one, integrated model are discussed.