CEAI_LOGO

Modelling the Cutting Process using Response Surface Methodology and Artificial Intelligence Approach: a Comparative Study

Authors
  • Drgaos Arotaritei

    "Grigore T. Popa" University of Medicine and Pharmacy, Iasi, Romania

  • George Constantin

    University Politehnica of Bucharest, Engineering and Management of Technological Systems, Machines and Manufacturing Systems Department, Bucharest, Romania

  • Corina Constantin

    Metallurgical Enterprise for Aeronautics METAV, Bucharest, Romania

  • Andrea Loredana Cretu

    "Grigore T. Popa" University of Medicine and Pharmacy, Iasi, Romania

Abstract
The paper deals with the milling force modelling concerning average and maximum forces for a set of four materials. The main purpose of the work is to obtain a function of three variables (cutting depth, feed per toot and cutting speed) using response surface methodology (RSM), and artificial intelligence approach (AI). A new method based on hybrid multiple regression (HMR) using RSM, and also a novel algorithm are proposed. In AI, determination of the optimal neural network of fuzzy neural network is an important aspect when we use these models for prediction. Differential genetic algorithms for variable length genotype are proposed to optimize simultaneously both structure and parameters for AI structures. A comparative study based on performance analysis is made also.
References
Downloads
Published
2014-06-25
Section
Articles