Application of regression and artificial neural network analysis in modelling of tool-chip interface temperature in machining


EXPERT SYSTEMS WITH APPLICATIONS, vol.38, no.9, pp.11651-11656, 2011 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 38 Issue: 9
  • Publication Date: 2011
  • Doi Number: 10.1016/j.eswa.2011.03.044
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Page Numbers: pp.11651-11656
  • Keywords: Temperature prediction, Artificial neural network, Regression analysis, Machining, Tool-chip interface temperature, SURFACE-ROUGHNESS, RESIDUAL-STRESSES, FLANK WEAR, PREDICTION, STEEL, HEAT
  • Gazi University Affiliated: Yes


In this paper, the regression analysis (RA) and artificial neural network (ANN) are presented for the prediction of tool-chip interface temperature depends on cutting parameters in machining. The RA and ANN model for prediction tool-chip interface temperature are developed and mathematical equations derived for tool-chip interface temperature prediction are obtained. The tool-chip interface temperature results obtained from mathematical equations with RA and ANN model and the experimental results available in the literature obtained by using AISI 1117 steel work piece with embedded K type thermocouple into the uncoated cutting tool (Korkut, Boy, Karacan, & Seker, 2007) are compared. The coefficient of determination (R-2) both training and testing data for temperature prediction in the ANN model are determined as 0.999791289 and 0.997889303 whereas; R-2 for both training and testing data in the RA model are computed as 0.999063 and 0.999427, respectively. The correlation obtained by the training ANN model are better than the one obtained by training RA model. The training ANN model with the Levenberg-Marquardt (LM) algorithm provides more accurate prediction and is quite useful in the calculation of tool-chip interface temperature when compared with the trained RA method in machining. On the other hand, prediction values obtained the testing RA model is slightly better performance than the testing ANN model. The results show that the tool-chip interface temperature equation derived from RA and ANN model can be used for prediction. (C) 2011 Elsevier Ltd. All rights reserved.