Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
4.4
2.9
Journals
Metals
Special Issues
Application of Neural Networks in Processing of Metallic Materials
share announcement

Application of Neural Networks in Processing of Metallic Materials

A special issue of Metals (ISSN 2075-4701). This special issue belongs to the section "Metal Casting, Forming and Heat Treatment".

Deadline for manuscript submissions: closed (31 March 2023) | Viewed by 11064

Special Issue Editor

Dr. Iztok Peruš

E-Mail Website
Guest Editor
Faculty of Civil Engineering, Transportation Engineering and Architecture, University of Maribor, Smetanova ulica 17, 2000 Maribor, Slovenia
Interests: processing of metallic materials; metallurgy; microstructure; neural networks; artificial intelligence; process chains; quality of products; energy consumption; sustainable metal production; blockchain technology

Special Issue Information

Dear Colleagues,

The processing of metallic materials is one of the most demanding and expensive processes, as it requires several intermediate stages (i.e., molten metal or raw material; casting and solidification; hot, warm and/or cold working; shaping of products; heat and surface treatment), and involves high energy consumption. For this reason, it is desirable to optimise the production process (process chain) in terms of energy, mechanical properties, specific product properties, and technological yield. This can be achieved with a better and deeper understanding of the influence of process parameters, the chemical composition, as well as the production equipment used on the final properties of the products. Thus, the properties of the products are related to the technological path of the material in the production process, the chemical composition of the materials used, the production equipment used, etc. Physical phenomena that take place in materials during their production have a very complex and highly nonlinear dependence on the technological parameters that influence the evolution of the microstructure and determine its final properties. The main reason for the complexity is the multiscale nature of metal processing, which makes it difficult to develop reliable and sufficiently accurate physical models for metal material processing simulations that are also computationally undemanding to be potentially used for the on-line control of production. On the other hand, phenomenological models have many other deficiencies. However, recent advances in AI—especially in the field of modern artificial neural networks—allow the development of efficient models that can optimize production (efficient use of energy, lower production costs, improvement of desired mechanical properties, etc.).

To get closer to a greener and sustainable future of metal processing, an efficient approach is necessary. Therefore, the purpose of this Special Issue is to present works dealing with the development of novel approaches—primarily the development and application of artificial neural networks in various metal processing operations (i.e., molten metal processing, raw material processing, preparing of initial material before the deformation process, casting and solidification shaping of product and semi-product, hot and/or cold working, heat and surface treatment, etc.). However, the sharing of research results in metal processing by applying other novel approaches related to artificial intelligence and/or disruptive technologies such as IoT (Internet of Things) and/or blockchain technology is also welcome. The latter can help in controlling work processes and ensuring the immutability of process parameters.

Dr. Iztok Peruš
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Metals is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • processing of metallic materials
  • metallurgy
  • microstructure
  • neural networks
  • artificial intelligence
  • process chains
  • quality of products
  • energy consumption
  • sustainable metal production
  • blockchain technology

Published Papers (6 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

13 pages, 1259 KiB  
Article
Neural Network as a Tool for Design of Amorphous Metal Alloys with Desired Elastoplastic Properties
by Bulat N. Galimzyanov, Maria A. Doronina and Anatolii V. Mokshin
Metals 2023, 13(4), 812; https://doi.org/10.3390/met13040812 - 21 Apr 2023
Cited by 3 | Viewed by 1445
Abstract
The development and implementation of the methods for designing amorphous metal alloys with desired mechanical properties is one of the most promising areas of modern materials science. Here, the machine learning methods appear to be a suitable complement to empirical methods related to [...] Read more.
The development and implementation of the methods for designing amorphous metal alloys with desired mechanical properties is one of the most promising areas of modern materials science. Here, the machine learning methods appear to be a suitable complement to empirical methods related to the synthesis and testing of amorphous alloys of various compositions. In the present work, a method is proposed a method to determine amorphous metal alloys with mechanical properties closest to those required. More than 50,000 amorphous alloys of different compositions have been considered, and the Young’s modulus E and the yield strength σy have been evaluated for them by the machine learning model trained on the fundamental physical properties of the chemical elements. Statistical treatment of the obtained results reveals that the fundamental physical properties of the chemical element with the largest mass fraction are the most significant factors, whose values correlate with the values of the mechanical properties of the alloys, in which this element is involved. It is shown that the values of the Young’s modulus E and the yield strength σy are higher for amorphous alloys based on Cr, Fe, Co, Ni, Nb, Mo and W formed by the addition of semimetals (e.g., Be, B, Al, Sn), nonmetals (e.g., Si and P) and lanthanides (e.g., La and Gd) than for alloys of other compositions. Increasing the number of components in alloy from 2 to 7 and changing the mass fraction of chemical elements has no significantly impact on the strength characteristics E and σy. Amorphous metal alloys with the most improved mechanical properties have been identified. In particular, such extremely high-strength alloys include Cr80B20 (among binary), Mo60B20W20 (among ternary) and Cr40B20Nb10Pd10Ta10Si10 (among multicomponent). Full article
(This article belongs to the Special Issue Application of Neural Networks in Processing of Metallic Materials)
►▼ Show Figures

Figure 1

14 pages, 277 KiB  
Article
Determination of the Influence of Steelmaking Parameters on Surface Defects in Quarto Plates
by Matjaž Knap and Boštjan Bradaškja
Metals 2023, 13(3), 536; https://doi.org/10.3390/met13030536 - 07 Mar 2023
Viewed by 885
Abstract
This work aimed to establish a relationship between the parameters affecting the steelmaking process and the quality of the quarto plates. We knew that the main causes of product defects in the plates were in the steelmaking process, so we sought to make [...] Read more.
This work aimed to establish a relationship between the parameters affecting the steelmaking process and the quality of the quarto plates. We knew that the main causes of product defects in the plates were in the steelmaking process, so we sought to make changes to the process. All units in the steelmaking plant were equipped with sensors to control the working parameters, which were regularly stored in databases. These data are supplemented by the chemical composition of the molten steel at various stages of the process. To organise and analyse the huge amounts of data, data mining tools included in the Orange Software were used. For industrial use, the tree algorithm seems to be the most suitable, but we also used other models based on artificial intelligence. Unexpectedly, we obtained evidence of self-regulation and robustness in the steelmaking process. Another important result was that some additional parameters should be measured and analysed regularly, at least the amount of oligo-elements in the molten steel and the basicity of the final refining slag. Full article
(This article belongs to the Special Issue Application of Neural Networks in Processing of Metallic Materials)
25 pages, 12458 KiB  
Article
Optimization of Thermomechanical Processing under Double-Pass Hot Compression Tests of a High Nb and N-Bearing Austenitic Stainless-Steel Biomaterial Using Artificial Neural Networks
by Gláucia Adriane de S. Sulzbach, Maria Verônica G. Rodrigues, Samuel F. Rodrigues, Marcos Natan da S. Lima, Rodrigo de C. Paes Loureiro, Denis Fabrício S. de Sá, Clodualdo Aranas, Jr., Glaucia Maria E. Macedo, Fulvio Siciliano, Hamilton F. Gomes de Abreu, Gedeon S. Reis and Eden S. Silva
Metals 2022, 12(11), 1783; https://doi.org/10.3390/met12111783 - 23 Oct 2022
Cited by 3 | Viewed by 1352
Abstract
Physical simulation is a useful tool for examining the events that occur during the multiple stages of thermomechanical processing, since it requires no industrial equipment. Instead, it involves hot deformation testing in the laboratory, similar to industrial-scale processes, such as controlled hot rolling [...] Read more.
Physical simulation is a useful tool for examining the events that occur during the multiple stages of thermomechanical processing, since it requires no industrial equipment. Instead, it involves hot deformation testing in the laboratory, similar to industrial-scale processes, such as controlled hot rolling and forging, but under different conditions of friction and heat transfer. Our purpose in this work was to develop an artificial neural network (ANN) to optimize the thermomechanical behavior of stainless-steel biomaterial in a double-pass hot compression test, adapted to the Arrhenius–Avrami constitutive model. The method consists of calculating the static softening fraction (Xs) and mean recrystallized grain size (ds), implementing an ANN based on data obtained from hot compression tests, using a vacuum chamber in a DIL 805A/D quenching dilatometer at temperatures of 1000, 1050, 1100 and 1200 °C, in passes (ε1 = ε2) of 0.15 and 0.30, a strain rate of 1.0 s−1 and time between passes (tp) of 1, 10, 100, 400, 800 and 1000 s. The constitutive analysis and the experimental and ANN-simulated results were in good agreement, indicating that ASTM F-1586 austenitic stainless steel used as a biomaterial undergoes up to Xs = 40% of softening due solely to static recovery (SRV) in less than 1.0 s interval between passes (tp), followed by metadynamic recrystallization (MDRX) at strains greater than 0.30. At T > 1050 °C, the behavior of the softening curves Xs vs. tp showed the formation of plateaus for long times between passes (tp), delaying the softening kinetics and modifying the profile of the curves produced by the moderate stacking fault energy, γsfe = 69 mJ/m2 and the strain-induced interaction between recrystallization and precipitation (Z-phase). Thus, the use of this ANN allows one to optimize the ideal thermomechanical parameters for distribution and refinement of grains with better mechanical properties. Full article
(This article belongs to the Special Issue Application of Neural Networks in Processing of Metallic Materials)
►▼ Show Figures

Figure 1

18 pages, 4802 KiB  
Article
Prediction of Spherical Sheet Springback Based on a Sparrow-Search-Algorithm-Optimized BP Neural Network
by Lei Li, Zheng Zhang and Binjiang Xu
Metals 2022, 12(8), 1377; https://doi.org/10.3390/met12081377 - 19 Aug 2022
Cited by 4 | Viewed by 1749
Abstract
Springback is an unavoidable problem in cold-forming processes and affects the efficiency and quality of the processing of outer sheets for ships. Therefore, effective control and prediction of sheet-forming springback is particularly important in the field of cold-bending processes. To this end, this [...] Read more.
Springback is an unavoidable problem in cold-forming processes and affects the efficiency and quality of the processing of outer sheets for ships. Therefore, effective control and prediction of sheet-forming springback is particularly important in the field of cold-bending processes. To this end, this paper presents research on cold-bending springback prediction based on a study of the multipoint cold-bending process combined with intelligent algorithms, as well as research on the multipoint cold-bending production of ship-hull plates. The forming process of spherical sheets was simulated by a finite element simulation. The amount of springback under different processes was studied, and the forming state and springback state were briefly analyzed. Then an in-depth study of machine learning was carried out, and the sparrow search algorithm (SSA) was introduced based on a back-propagation neural network (BPNN). The purpose of this integration was to prevent the BP neural network model from falling into local optimal solution problems. Then simulation data were obtained with the help of a simulation to build a backpropagation neural network prediction model, which was optimized based on the sparrow search algorithm, and training tests were conducted. Then the prediction results of the model were compared with the simulation data to verify that the prediction accuracy performance of the sparrow-search-algorithm-optimized BPNN model was improved. Finally, the prediction model based on the SSA–BPNN algorithm was compared with the prediction models of different algorithms, and the prediction results showed that SSA–BPNN outperformed other algorithms in prediction accuracy and speed; its prediction error was within 4%, which meets on-site processing requirements. The sparrow-search-algorithm-based optimization of BPNN was confirmed to have strong applicability in springback prediction. Full article
(This article belongs to the Special Issue Application of Neural Networks in Processing of Metallic Materials)
►▼ Show Figures

Figure 1

14 pages, 4492 KiB  
Article
Contour Maps for Simultaneous Increase in Yield Strength and Elongation of Hot Extruded Aluminum Alloy 6082
by Iztok Peruš, Goran Kugler, Simon Malej and Milan Terčelj
Metals 2022, 12(3), 461; https://doi.org/10.3390/met12030461 - 09 Mar 2022
Cited by 3 | Viewed by 1672
Abstract
In this paper, the Conditional Average Estimator artificial neural network (CAE ANN) was used to analyze the influence of chemical composition in conjunction with selected process parameters on the yield strength and elongation of an extruded 6082 aluminum alloy (AA6082) profile. Analysis focused [...] Read more.
In this paper, the Conditional Average Estimator artificial neural network (CAE ANN) was used to analyze the influence of chemical composition in conjunction with selected process parameters on the yield strength and elongation of an extruded 6082 aluminum alloy (AA6082) profile. Analysis focused on the optimization of mechanical properties as a function of casting temperature, casting speed, addition rate of alloy wire, ram speed, extrusion ratio, and number of extrusion strands on one side, and different contents of chemical elements, i.e., Si, Mn, Mg, and Fe, on the other side. The obtained results revealed very complex non-linear relationships between all of these parameters. Using the proposed approach, it was possible to identify the combinations of chemical composition and process parameters as well as their values for a simultaneous increase of yield strength and elongation of extruded profiles. These results are a contribution of the presented study in comparison with published research results of similar studies in this field. Application of the proposed approach, either in the research and/or in industrial aluminum production, suggests a further increase in the relevant mechanical properties. Full article
(This article belongs to the Special Issue Application of Neural Networks in Processing of Metallic Materials)
►▼ Show Figures

Figure 1

12 pages, 7787 KiB  
Article
Modelling of the Steel High-Temperature Deformation Behaviour Using Artificial Neural Network
by Alexander Churyumov, Alena Kazakova and Tatiana Churyumova
Metals 2022, 12(3), 447; https://doi.org/10.3390/met12030447 - 04 Mar 2022
Cited by 26 | Viewed by 2804
Abstract
Hot forming is an essential part of the manufacturing of most steel products. The hot deformation behaviour is determined by temperature, strain rate, strain and chemical composition of the steel. To date, constitutive models are constructed for many steels; however, their specific chemical [...] Read more.
Hot forming is an essential part of the manufacturing of most steel products. The hot deformation behaviour is determined by temperature, strain rate, strain and chemical composition of the steel. To date, constitutive models are constructed for many steels; however, their specific chemical composition limits their application. In this paper, a novel artificial neural network (ANN) model was built to determine the steel flow stress with high accuracy in the wide range of the concentration of the elements in high-alloyed, corrosion-resistant steels. The additional compression tests for stainless Cr12Ni3Cu steel were carried out at the strain rates of 0.1–10 s−1 and the temperatures of 900–1200 °C using thermomechanical simulator Gleeble 3800. The ANN-based model showed high accuracy for both training (the error was 6.6%) and approvement (11.5%) datasets. The values of the effective activation energy for experimental (410 ± 16 kJ/mol) and predicted peak stress values (380 ± 29 kJ/mol) are in good agreement. The implementation of the constructed ANN-based model showed a significant influence of the Cr12Ni3Cu chemical composition variation within the grade on the flow stress at a steady state of the hot deformation. Full article
(This article belongs to the Special Issue Application of Neural Networks in Processing of Metallic Materials)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-6
Back to TopTop