Design Optimization of Microalloyed Steels Using Thermodynamics Principles and Neural-Network-Based Modeling

Mohanty, Itishree; Chintha, Appa Rao; Kundu, Saurabh

doi:10.1007/s11661-018-4540-4

Cited by 8 publications

(4 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the development of an artificial neural network, training and test databases are usually used, and a validation database can also be used [11][12][13][14][15][16][17]. The training database is used to obtain the best parameter ratio of the artificial neural network, the validation database assists in the artificial neural network evaluation process during training, and the test database aims at the evaluation of the artificial neural network on unknown data.…”

Section: Data Chemical Systemmentioning

confidence: 99%

“…Artificial neural networks (ANN) are computational models capable of establishing mathematical relationships in order to approach an optimal value, by updating these mathematical relationships in a finite number of interactions. Artificial neural networks are widely used in classification, resulting in discrete variables for image processing and recognition [11] with image-based search engines and biomedical diagnosis [12] and regression where the result is a continuous variable for the prediction of mechanical properties in microalloyed steels [13] and nickel superalloys [14] and in the prediction of viscosity in metallurgical slags [15] and oxide liquids [16].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Viskositas: Viscosity Prediction of Multicomponent Chemical Systems

dos¹

2022

Preprint

View full text Add to dashboard Cite

Viscosity in the metallurgical and glass industry plays a fundamental role in its production processes, also in the area of geophysics. As its experimental measurement is financially expensive, also in terms of time, several mathematical models were built to provide viscosity results as a function of several variables, such as chemical composition and temperature, in linear and nonlinear models. A database was built in order to produce a nonlinear model by artificial neural networks by variation of hyperparameters to provide reliable predictions of viscosity in relation to chemical systems and temperatures. The model produced named Viskositas demonstrated better statistical evaluations of mean absolute error, standard deviation and coefficient of determination (R 2 ) in relation to the test database when compared to different models from literature and 1 commercial model, offering predictions with lower errors, less variability and less generation of outliers.

show abstract

Section: Data Chemical Systemmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Viskositas: Viscosity Prediction of Multicomponent Chemical Systems

dos¹

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Computer-aided modeling is used in scientific research and the industry. It is a relatively inexpensive and effective method to optimize, among others, the chemical composition and process conditions to achieve the required material properties [ 11 , 12 , 13 , 14 ]. The increasing availability of material databases and advances in machine learning methods are creating new opportunities for material design [ 15 , 16 , 17 , 18 ].…”

Section: Introductionmentioning

confidence: 99%

A Hybrid Method for Calculating the Chemical Composition of Steel with the Required Hardness after Cooling from the Austenitizing Temperature

Trzaska,

Sitek

2023

Materials

View full text Add to dashboard Cite

The article presents a hybrid method for calculating the chemical composition of steel with the required hardness after cooling from the austenitizing temperature. Artificial neural networks (ANNs) and genetic algorithms (GAs) were used to develop the model. Based on 550 diagrams of continuous cooling transformation (CCT) of structural steels available in the literature, a dataset of experimental data was created. Artificial neural networks were used to develop a hardness model describing the relationship between the chemical composition of the steel, the austenitizing temperature, and the hardness of the steel after cooling. A genetic algorithm was used to identify the chemical composition of the steel with the required hardness. The value of the objective function was calculated using the neural network model. The developed method for identifying the chemical composition was implemented in a computer application. Examples of calculations of mass concentrations of steel elements with the required hardness after cooling from the austenitizing temperature are presented. The model proposed in this study can be a valuable tool to support chemical composition design by reducing the number of experiments and minimizing research costs.

show abstract

“…Mohanty and Bhattacharjee [20] explained in detail the success of ANN in steel industry in predicting and controlling processes by understanding the physics behind it. Mohanty et al [21] has shown ANN could be used in estimating and optimizing properties of microalloyed steel,, the result has been validated by thermodynamic calculation and plant trial. It has also been used to design alloys of different types of steels.…”

Section: Introductionmentioning

confidence: 99%

Prediction of properties over the length of the coil during thermo-mechanical processing using DNN

Mohanty

Banerjee

Santara

et al. 2020

Ironmaking & Steelmaking

Self Cite

View full text Add to dashboard Cite

Certain mechanical properties of steel, such as elongation percentage, yield strength and ultimate tensile strength, form the basis for classification of steel coils into various categories. Methods to improve the prediction of such properties, using multiple chemical and physical process parameters, have remained an integral area of research in steel plants. In this paper, an important parameter, that is, the run-out table cooling profile of a hot strip mill coil, is considered along with the customary process parameters. This additional parameter allows a deep neural network-based model to predict the mechanical properties of steel for multiple segments along the entire length of the coil instead of the established single-segment property prediction process with very high R 2 value.

show abstract

Design Optimization of Microalloyed Steels Using Thermodynamics Principles and Neural-Network-Based Modeling

Cited by 8 publications

References 34 publications

Viskositas: Viscosity Prediction of Multicomponent Chemical Systems

Viskositas: Viscosity Prediction of Multicomponent Chemical Systems

A Hybrid Method for Calculating the Chemical Composition of Steel with the Required Hardness after Cooling from the Austenitizing Temperature

Prediction of properties over the length of the coil during thermo-mechanical processing using DNN

Contact Info

Product

Resources

About