Skip to main content
Materials TransactionsVolume 56, Issue 6, 2015, Pages 835-839

Chemometric approach for mechanical properties prediction during the electromagnetic casting process(Article)(Open Access)

  Save all to author list
  • aInstitute for Technology of Nuclear and Other Mineral Raw Materials, Franchet d'Esperey 86, Belgrade, 11000, Serbia
  • bFaculty of Technical Sciences, University of Kragujevac, Svetog Save 65, Cacak, 32000, Serbia
  • cInstitute of General and Physical Chemistry, University of Belgrade, Studentski Trg 12-16, Belgrade, 11000, Serbia
  • dFaculty of Engineering, University of Kragujevac, Sestre Janjic 6, Kragujevac, 34000, Serbia

Abstract

In this study the mechanical properties (reduction of area, S0, tensile strength, Rm, yield strength, Rp, and elongation, A) of EN AW 7075 aluminum alloy obtained by electromagnetic casting were investigated at different operating parameters: frequency (V), field strength (T) and current intensity (I). The predictive mathematical models using Response Surface Methodology, with second order polynomial (SOP) regression models, and Artificial Neural Network model (ANN), were afterwards compared to obtained experimental results. Analysis of variance and posthoc Tukey's HSD test at 95% confidence limit ("honestly significant differences") have been utilised to show significant differences between various samples. SOP models showed good prediction capabilities, with high coefficients of determination (r2), 0.5310.977, while ANN model performed even better prediction accuracy: 0.8000.992. The optimal samples were chosen depending on mechanical properties of the product (S0 = 50.49mm2, Rm = 405.75Nmm-2, Rp = 302.49Nmm-2, A = 6.86%), using optimal operating parameters (V = 30 Hz, I = 250 A, T = 18 × 10-3 At). © 2015 The Japan Institute of Metals and Materials.

Author keywords

Aluminum alloyCastingMechanical propertiesNeural network modelingPrediction

Indexed keywords

Engineering controlled terms:AluminumCastingForecastingMechanical propertiesNeural networksRegression analysisTensile strength
Engineering uncontrolled termsArtificial neural network modelsElectromagnetic castingHonestly significant differencesNeural network modelOperating parametersPrediction capabilityResponse surface methodologySecond-order polynomial
Engineering main heading:Aluminum alloys
  • ISSN: 13459678
  • CODEN: MTARC
  • Source Type: Journal
  • Original language: English
  • DOI: 10.2320/matertrans.M2015058
  • Document Type: Article
  • Publisher: Japan Institute of Metals (JIM)

  Pataric, A.; Institute for Technology of Nuclear and Other Mineral Raw Materials, Franchet d'Esperey 86, Belgrade, Serbia
© Copyright 2015 Elsevier B.V., All rights reserved.

Cited by 2 documents

Wu, S.-W. , Yang, J.
A convolutional neural network-based model for predicting lime utilization ratio in the KR desulfurization process
(2021) Metallurgical Research and Technology
Wu, S. , Yang, J. , Cao, G.
Elevating Prediction Performance for Mechanical Properties of Hot-Rolled Strips by Using Semi-Supervised Regression and Deep Learning
(2020) IEEE Access
View details of all 2 citations
Inform me when this document is cited in Scopus:
Set citation alert Set citation feed
{"topic":{"name":"Desulfurization; Aluminum Oxide; Bauxite","id":76349,"uri":"Topic/76349","prominencePercentile":57.58223,"prominencePercentileString":"57.582","overallScholarlyOutput":0},"dig":"d593dcff375a0fa2b0478f916dcf1556638fc8f492bdfdbffd6ba6c6c2a6c9f0"}

SciVal Topic Prominence

Topic:
Prominence percentile: