Statistical Data-Driven Model for Hardness Prediction in Austempered Ductile Irons

Rodríguez-Rosales, Nelly Abigaíl; Montes-González, Félix Alan; Gómez-Casas, Oziel; Gómez-Casas, Josué; Galindo-Valdés, Jesús Salvador; Ortiz-Cuellar, Juan Carlos; Martínez-Villafañe, J.F.; García-Navarro, Daniel; Muñiz-Valdez, Carlos Rodrigo

doi:10.3390/met12040676

Cited by 3 publications

(1 citation statement)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The fact that there are contradictions in a set, even if they are numerous, does not make it impossible to build a model. The properties of ductile iron have been repeatedly modeled with the use of soft mathematical models, but prediction models were usually used such as: multiple linear regression, artificial neural networks, support vector machine, projection pursuit regression (Kochański et al, 2012;Perzyk & Kochański, 2001;Perzyk et al, 2015;Rodríguez-Rosales et al, 2022;Wilk-Kołodziejczyk et al, 2018). Less frequently, work was undertaken on property modeling with the use of rule-creating tools based on the theory of fuzzy sets and decision trees (Kochański et al, 2013(Kochański et al, , 2014Perzyk & Soroczyński, 2008Perzyk et al, 2011).…”

Section: Introductionmentioning

confidence: 99%

Rule modeling of ADI cast iron structure for contradictory data

Soroczyński¹,

Biernacki²,

Kochański³

2022

cmms

View full text Add to dashboard Cite

Ductile iron is a material that is very sensitive to the conditions of crystallization. Due to this fact, the data on the cast iron properties obtained in tests are significantly different and thus sets containing data from samples are contradictory, i.e. they contain inconsistent observations in which, for the same set of input data, the output values are significantly different.The aim of this work is to try to determine the possibility of building rule models in conditions of significant data uncertainty. The paper attempts to determine the impact of the presence of contradictory data in a data set on the results of process modeling with the use of rule-based methods. The study used the well-known dataset (Materials Algorithms Project Data Library, n.d.) pertaining to retained austenite volume fraction in austempered ductile cast iron. Two methods of rulebased modeling were used to model the volume of the retained austenite: the decision trees algorithm (DT) and the rough sets algorithm (RST).The paper demonstrates that the number of inconsistent observations depends on the adopted data discretization criteria. The influence of contradictory data on the generation of rules in both algorithms is considered, and the problems that can be generated by contradictory data used in rule modeling are indicated.

show abstract

Section: Introductionmentioning

confidence: 99%

Rule modeling of ADI cast iron structure for contradictory data

Soroczyński¹,

Biernacki²,

Kochański³

2022

cmms

View full text Add to dashboard Cite

show abstract

Effect of Austenitization Time on Corrosion and Wear Resistance in Austempered Ductile Iron

Montes González,

Magaña Hernández,

Miranda Pérez

et al. 2024

Inter Metalcast

View full text Add to dashboard Cite

Regression Analysis and Optimum Values of Austempering Affecting Mechanical Properties of Compacted Graphite Iron

Jakubus,

Soiński,

Mierzwa

et al. 2024

Materials

View full text Add to dashboard Cite

The study examined the effect of heat treatment parameters of compacted graphite iron (CGI) on the mechanical properties of the material. The microstructure was characterized using optical microscopy, scanning electron microscopy (SEM), and transmission electron microscopy (TEM). Three levels of heat treatment parameters were adopted considering the orthogonal test plan 24. The effects of austenitizing temperature and time and austempering on tensile strength, yield strength, and elongation were analyzed. Polynomial regression was chosen because it extends linear regression and allows for modeling more complex, nonlinear relationships between variables. Total regression models were determined for each dataset. The models for tensile strength (Rm) had an approximately 82% coefficient of determination, for yield strength (R0.2) around 50%, and for elongation (A5) around 80%. For optimization, the response surface method (RSM) was used. The results obtained were compared with the proposed mathematical models. The ANOVO results showed that austempering temperature (Tpi) had the greatest effect on each parameter studied. The optimal conditions for the analyzed parameters, assuming tensile strength and yield strength at the maximum level and an elongation of about 0.7%, are obtained for the following heat treatment parameters: Tγ = 890 °C; Tpi = 290 °C; τγ = 120 min; τpi = 150 min.

show abstract

Statistical Data-Driven Model for Hardness Prediction in Austempered Ductile Irons

Cited by 3 publications

References 55 publications

Rule modeling of ADI cast iron structure for contradictory data

Rule modeling of ADI cast iron structure for contradictory data

Effect of Austenitization Time on Corrosion and Wear Resistance in Austempered Ductile Iron

Regression Analysis and Optimum Values of Austempering Affecting Mechanical Properties of Compacted Graphite Iron

Contact Info

Product

Resources

About