Comparison of Regression Model and Artificial Neural Network Model for the Prediction of Volume Percent of Diamond Deposition in Ni-Diamond Composite Coating

• Autor(a) principal: Ramanathan,K.
• Data de Publicação: 2008
• Outros Autores: Periasamy,V.M., Natarajan,U.
• Tipo de documento: Artigo
• Idioma: eng
• Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
• Texto Completo: http://scielo.pt/scielo.php?script=sci_arttext&pid=S0872-19042008000400005
• topic: Volume fraction of diamond deposition (Vfd); ANN; Regression models; Design of Experiments (DOE); Ni-diamond composite coating

Nickel-diamond composite coatings are produced by electro deposition using sedimentation techniques on mild steel substrate at various cathode current density, pH and temperature. Electro deposition was carried out from a conventional Watts bath. Natural diamond powder of 6-12 mm size was used in the study. The volume percent incorporation of diamond on the coated specimens was measured gravimetrically. Artificial Neural Network (ANN) and regression models (a mathematical model) were used to predict the volume percent incorporation of diamond in the Ni-diamond metal matrix. In this work, Volume fraction of diamond deposition (Vfd) was taken as response variable (output variable) and current density, pH and temperature were taken as input variables. The prediction of response variable was obtained with the help of empirical relation between the response variable and input variables using ANN and also through DOE. The predicted values of the responses by ANN and regression models were compared with the experimental values and their closeness with the experimental values was determined.