Filtreler

2012 - 20172
Filtreleri Sıfırla

Ayarlar

İndeks: Scopus × Konu: ANN ×

Arama Sonuçları

Listeleniyor 1 - 2 / 2
  • Küçük Resim
    Öğe
    Calculating molding parameters in plastic injection molds with ANN and developing software
    (Taylor & Francis, 2012-02) Çelik, Yahya Hışman; Özek, Cebeli
    In recent years, plastic injection molds are widely used for producing products in various areas, such as aerospace, automotive, medical, electronics, and toys. The quality of these products depends on correctly chosen molding parameters. In this study, a new package program (NPP)-Software that calculates various injection molding parameters was developed to mold plastic products obtained by plastic injection molding techniques using the model of artificial neural network (ANN). The Delphi programming language was used in the develop the (NPP)-Software. The developed (NPP)-Software was trained and tested using the Levenberg–Marquardt (LM) algorithm, the ANN. One-thousand three-hunderd pieces of data were collected, out of which 250 were used to train the network. The ANN is employed to find optimum molding parameters that enable minimum defects in the injection-molded part, such as volumetric shrinkage, injection time, and cooling time. The three parameters predicted, using the (NPP)-Software, were compared using experimental results.
  • Küçük Resim
    Öğe
    Küreselleştirme ısıl işlemi uygulanmış AISI 1050 çeliǧinin yüzey pürüzlülük deǧerlerinin yapay sinir aǧları ile modellenmesi
    (IEEE, 2017-10-30) Baday, Şehmus; Başak, Hüdayim; Sönmez, Fikret
    Estimation of surface roughness values, which is an indication of workpiece quality, is important in terms of reducing the cost and duration of machining. In this study, the surface roughness values of the medium carbon steel subjected to the spheronization heat treatment have estimated by artificial neural networks. ANN network model have been created by being chosen feedforward back propagation network model, the adoption of network structure and learning function LEARNGDM, TRAINLM as training algorithm, MSE for assessment of network performance and two hidden layers. The value of each neuron in the network have been transferred another layer by TANSIG, LOGSIG and PURELIN transfer functions. As a result, the artificial neural networks trained and tested have been found to be easy to use for estimating surface roughness values with a high percentage of R = 0.99001 according to MSE performance.