Prediction of Surface Roughness using double ANN and the Efficient Machining Database Building Scheme in High Speed Machining

고속가공에서 2중 신경망을 이용한 표면거칠기 예측과 가공DB 구축 효율화 방안

  • 원종률 (한국생산기술연구원 나노가공팀) ;
  • 남성호 (한국생산기술연구원 나노가공팀) ;
  • 유송민 (경희대학교 기계공학과) ;
  • 이석우 (한국생산기술연구원 나노가공팀) ;
  • 최헌종 (한국생산기술연구원 나노가공팀)
  • Published : 2004.10.01

Abstract

In this paper, a double artificial neural network (ANN) approach and the efficient machining database building scheme are presented for the prediction of surface roughness in high-speed machining. In this approach, 4 machining parameters and used for the prediction of cutting force components, and the combinations of 4 parameters and the predicted cutting force components are finally used for the prediction of surface roughness. The experimental results comparing the these results with the predicted values using simple 4 input nodes have been also investigated to verify the effectiveness of the proposed approach.

Keywords