Chemometric Approach for Mechanical Properties Prediction during the Electromagnetic Casting Process

• Pataric Aleksandra

  Institute for Technology of Nuclear and Other Mineral Raw Materials

• Gulišija Zvonko

  Institute for Technology of Nuclear and Other Mineral Raw Materials

• Jordovic Branka

  Faculty of Technical Sciences, University of Kragujevac

• Pezo Lato

  Institute of General and Physical Chemistry, University of Belgrade

• Mihailovic Marija

  Institute for Technology of Nuclear and Other Mineral Raw Materials

• Stefanovic Milentije

  Faculty of Engineering, University of Kragujevac

抄録

In this study the mechanical properties (reduction of area, S₀, tensile strength, R_m, yield strength, R_p, 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 post-hoc 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), 0.531–0.977, while ANN model performed even better prediction accuracy: 0.800–0.992. The optimal samples were chosen depending on mechanical properties of the product (S₀ = 50.49 mm², R_m = 405.75 N mm⁻², R_p = 302.49 N mm⁻², A = 6.86%), using optimal operating parameters (V = 30 Hz, I = 250 A, T = 18 × 10⁻³ At).

収録刊行物

• MATERIALS TRANSACTIONS

  MATERIALS TRANSACTIONS 56 (6), 835-839, 2015

  公益社団法人 日本金属学会

キーワード

• casting
• mechanical properties
• neural network modeling
• prediction
• aluminum alloy

詳細情報

• CRID: 1390282679231214720
• NII論文ID: 130005072161
• NII書誌ID: AA1151294X
• DOI: 10.2320/matertrans.m2015058
• ISSN: 13475320
• ISSN: 13459678
• NDL書誌ID: 026412792
• Web Site: https://ndlsearch.ndl.go.jp/books/R000000004-I026412792
• Web Site: https://www.jstage.jst.go.jp/article/matertrans/56/6/56_M2015058/_pdf
• 本文言語コード: en
• データソース種別:
  • JaLC
  • NDL
  • Crossref
  • CiNii Articles
• 抄録ライセンスフラグ: 使用不可