Artificial neural network prediction of aging effects on the wear behavior of IN706 superalloy

Palavar O., ÖZYÜREK D. , KALYON A.

MATERIALS & DESIGN, cilt.82, ss.164-172, 2015 (SCI İndekslerine Giren Dergi) identifier identifier

  • Cilt numarası: 82
  • Basım Tarihi: 2015
  • Doi Numarası: 10.1016/j.matdes.2015.05.055
  • Sayfa Sayıları: ss.164-172


In this study, the effect of aging parameters on wear behavior of PM Inconel 706 (IN 706) superalloy was experimentally investigated and an ANN model was developed to predict weight loss after wear tests. IN 706 superalloy powders were cold pressed (700 MPa) and sintered at 1270 degrees C for 90 min. The sintered components were gradually aged for 16 h at 730 degrees C and for 12-20 h at 620 degrees C. The samples of IN706 superalloy were subjected to wear test at a constant sliding speed of 1 m/s under three different loads (30 N, 45 N and 60 N) and for five different sliding distances (400-2000 m). The results clearly showed that delta, gamma' and gamma '' phases were observed around grain boundaries of IN 706 superalloy aged for different periods. The highest hardness was measured for the samples aged for 12 h. Weight losses were found to increase as the sliding distance increased. Moreover, the ANN modeling of weight loss values for IN 706 superalloy gave effective results and can be successfully used to predict weight loss values in the parameters that were determined by the obtained high R-2 value. (C) 2015 Elsevier Ltd. All rights reserved.