Yazar "Demir, Halil" seçeneğine göre listele

Listeleniyor 1 - 3 / 3
  • Küçük Resim
    Öğe
    CNC TORNALAMA İŞLEMİNDE YÜZEY PÜRÜZLÜLÜĞÜ VE KESME KUVVETLERİNE ETKİ EDEN PARAMETRELERİN MATEMATİKSEL OLARAK MODELLENMESİ
    (Düzce Üniversitesi, 2014) Özlü, Barış; Demir, Halil; Nas, Engin
    Bu çalışmada; 30MnVS6 mikro alaşımlı çeliğinin tornalanmasında, kesme hızı (V) ve ilerleme miktarının (f) yüzey pürüzlülüğü (Ra) ve kesme kuvvetleri (Fc) üzerindeki etkileri ortaya konmuştur. Elde edilen yüzey pürüzlülüğü ve kesme kuvvetleri değerlerinin, kesme parametreleri ile olan ilişkilerinin matematiksel olarak modellenmesi için çeşitli eğri uydurma algoritmaları kullanılmıştır. Kullanılan bu eğri uydurma algoritmalarından elde edilen matematiksel modeller, korelasyon katsayıları (R2) kullanılarak değerlendirilmiştir.
  • Küçük Resim Yok
    Öğe
    MULTIPLE REGRESSION AND ANN MODELS FOR SURFACE QUALIFICATION OF CRYOGENICALLY-TREATED AISI 52100 BEARING STEEL
    (Scibulcom Ltd, 2013) Kara, Fuat; Çiçek, Adem; Demir, Halil
    This paper focuses on 2 different models, the multiple regression method and the artificial neural network (ANN), for predicting surface roughness (R-a). Experiments were conducted to measure surface roughness in the cylindrical grinding of AISI 52100 bearing steel which had been conventionally heat-treated and deep cryogenically treated (-145 degrees C). In order to compare the effects of holding time at the deep cryogenic temperatures, 5 different holding times (12, 24, 36, 48 and 60 h) were employed to obtain the optimum R-a. The cylindrical grinding test results showed that optimum R-a values were obtained on specimens cryogenically treated for 36 h. In addition, the prediction results showed that the ANN was superior to the multiple regression method in terms of prediction capability. Moreover, due to a higher determination coefficient (R-2) and lower root-mean-square error (RMSE) and mean error percentage (MEP), the ANN was notably successful in predicting the R-a.
  • Küçük Resim Yok
    Öğe
    Multiple regression and ANN models for surface quality of cryogenically-treated AISI 52100 bearing steel
    (2013) Kara, Fuat; Çiçek, Adem; Demir, Halil
    This paper focuses on 2 different models, the multiple regression method and the artificial neural network (ANN), for predicting surface roughness (Ra). Experiments were conducted to measure surface roughness in the cylindrical grinding of AISI 52100 bearing steel which had been conventionally heat-treated and deep cryogenically treated (-145°C). In order to compare the effects of holding time at the deep cryogenic temperatures, 5 different holding times (12, 24, 36, 48 and 60 h) were employed to obtain the optimum Ra. The cylindrical grinding test results showed that optimum R a values were obtained on specimens cryogenically treated for 36 h. In addition, the prediction results showed that the ANN was superior to the multiple regression method in terms of prediction capability. Moreover, due to a higher determination coefficient (R2) and lower root-mean-square error (RMSE) and mean error percentage (MEP), the ANN was notably successful in predicting the Ra.