Artificial neural network usage for determining solidus temperature of steels

Machů, Mario; Drozdová, Ľubomíra; Smetana, Bedřich; Zlá, Simona; Kawuloková, Monika

doi:10.37904/metal.2019.672

Cited by 3 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Less agreement may be due to the fact that up to 900 °C heat capacities could still be affected by the course of phase transformations they could also be affected by the dissolution of carbides in the range of 900 -1000 ° C. The fact that the heat capacities were measured up to 700 °C on the Setaram Sensys Evo TG / DSC and from 700 to 1580 °C on the Setaram MHTC 96 Line can also play a role. Table 3 shows results obtained by linear regression compared with results obtained by machine learning methods in previous work [19][20][21]. As for liquidus and solidus temperature, both methods seem to be suitable but linear regression slightly overperforms ANN.…”

Section: Specific Heat Capacitymentioning

confidence: 94%

Comparison of Linear Regression Models of Thermophysical Properties With Models Based on Machine Learning

Machů

Drozdová

Smetana

2022

METAL 2022 Conference Proeedings

View full text Add to dashboard Cite

The paper compares classical models for determining the thermophysical properties of steels based primarily on empirical equations derived using linear regression methods with models created using machine learning methods. The selected investigated quantities include phase transformation temperatures, specific heat capacity, coefficient of thermal expansion. The results of both approaches are verified on the measured data by methods of thermal analysis such as differential scanning calorimetry, differential thermal analysis and dilatometry. The methods are evaluated both in terms of the accuracy of predictions and in terms of the adequacy of use for a specific purpose, or in terms of the complexity of creating and using the model.

show abstract

Section: Specific Heat Capacitymentioning

confidence: 94%

Comparison of Linear Regression Models of Thermophysical Properties With Models Based on Machine Learning

Machů

Drozdová

Smetana

2022

METAL 2022 Conference Proeedings

View full text Add to dashboard Cite

show abstract

“…However, this requires highly resource-intensive algorithms, and the authors must use significant simplifications and assumptions in order to complete the simulation in an acceptable time. There are also attempts to use machine learning in this area [4,5].…”

Section: Introductionmentioning

confidence: 99%

Thermodynamic Simulation of Solidification of Ti-Containing Steels with Consideration for Possibility of Peritectic Transformation and Second Phase Precipitation

Горбачев

Popov

2022

Metals

View full text Add to dashboard Cite

An algorithm is proposed for predicting the phase composition of titanium-containing steels after solidification. The approach is based on thermodynamic calculations and provides for crystallization through the formation of ferrite and austenite, as well as a peritectic reaction. The algorithm takes into account the possibility of precipitation of TiN, TiS, MnS and TiC0.5S0.5 from the liquid phase upon crystallization. Two possible behaviors of ferrite upon crystallization are considered: frozen and fast diffusion of elements in the metal sublattice of this phase. Calculations illustrating the operation of the proposed algorithm have been performed.

show abstract

“…Using of methods based on artificial neural network (ANN) in material engineering became a promising way for predicting a wide variety of steel properties [1][2][3][4]. ANN also are capable of helping with design of new material of desired properties [5].…”

Section: Introductionmentioning

confidence: 99%

Determination of a coefficient of thermal expansion by machine learning

Machů

Drozdová

Smetana

et al. 2020

METAL 2020 Conference Proeedings

Self Cite

View full text Add to dashboard Cite

Objective of this work is to model the thermal expansion coefficients of selected steel grade and compare results with those measured by TMA method. Coefficient of thermal expansion is described as a function of steel composition (C, Mn, P, S, Si, Cr, Ni, Mo) and temperature.Experimental values are described and compared with model. Correlation analysis of these data sets is done. Presented model is based on using artificial neural network and represents a preliminary test of method capability to be used for such problems classfor predicting of thermophysical properties depending on composition and temperatre.

show abstract

Artificial neural network usage for determining solidus temperature of steels

Cited by 3 publications

References 0 publications

Comparison of Linear Regression Models of Thermophysical Properties With Models Based on Machine Learning

Comparison of Linear Regression Models of Thermophysical Properties With Models Based on Machine Learning

Thermodynamic Simulation of Solidification of Ti-Containing Steels with Consideration for Possibility of Peritectic Transformation and Second Phase Precipitation

Determination of a coefficient of thermal expansion by machine learning

Contact Info

Product

Resources

About