Modeling of wear behavior of Al/B4C composites produced by powder metallurgy


ŞAHİN İ., Bektas A., GÜL F., ÇİNİCİ H.

MATERIALS TESTING, cilt.59, sa.5, ss.491-496, 2017 (SCI-Expanded) identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 59 Sayı: 5
  • Basım Tarihi: 2017
  • Doi Numarası: 10.3139/120.111028
  • Dergi Adı: MATERIALS TESTING
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Sayfa Sayıları: ss.491-496
  • Anahtar Kelimeler: Wear modeling, metal-matrix composite, two-body abrasion, artificial neural network, ARTIFICIAL NEURAL-NETWORK, PREDICTION, SIZE, LOAD
  • Gazi Üniversitesi Adresli: Evet

Özet

Wear characteristics of composites, Al matrix reinforced with B4C particles percentages of 5, 10,15 and 20 produced by the powder metallurgy method were studied in this study. For this purpose, a mixture of Al and B4C powders were pressed under 650 MPa pressure and then sintered at 635 degrees C. The analysis of hardness, density and microstructure was performed. The produced samples were worn using a pin-on-disk abrasion device under 10, 20 and 30 N load through 500, 800 and 1200 mesh SiC abrasive papers. The obtained wear values were implemented in an artificial neural network (ANN) model having three inputs and one output using feed forward backpropagation Levenberg-Marquardt algorithm. Thus, the optimum wear conditions and hardness values were determined.