TY - JOUR
T1 - Estimation of shrinkage for near net-shape using a neural network approach
AU - Konak, Abdullah
AU - Kulturel-Konak, Sadan
AU - Smith, Alice E.
AU - Nettleship, Ian
N1 - Funding Information:
This project is s upported by NSF grant DMI-9800430 and by considerable in kind support by the industrial partner.
PY - 2003/4
Y1 - 2003/4
N2 - A neural network approach is presented for the estimation of shrinkage during a hot isostatic pressing (HIP) process of nickel-based superalloys for near net-shape manufacture. For the HIP process, the change in shape must be estimated accurately; otherwise, the finished piece will need excessive machining and expensive nickel-based alloy powder will be wasted (if shrinkage is overestimated) or the part will be scrapped (if shrinkage is underestimated). Estimating shape change has been a very difficult task in the powder metallurgy industry and approaches range from rules of thumb to sophisticated finite element models. However, the industry still lacks a reliable and general way to accurately estimate final shape. This paper demonstrates that the neural network approach is promising to estimate post-HIP dimensions from a combination of pre-HIP dimensions, powder characteristics and processing information. Compared to nonlinear regression models to estimate shrinkage, the neural network models perform very well. Furthermore, the models described in this paper can be used to find good HIP process settings, such as temperature and pressure, which can reduce operating costs.
AB - A neural network approach is presented for the estimation of shrinkage during a hot isostatic pressing (HIP) process of nickel-based superalloys for near net-shape manufacture. For the HIP process, the change in shape must be estimated accurately; otherwise, the finished piece will need excessive machining and expensive nickel-based alloy powder will be wasted (if shrinkage is overestimated) or the part will be scrapped (if shrinkage is underestimated). Estimating shape change has been a very difficult task in the powder metallurgy industry and approaches range from rules of thumb to sophisticated finite element models. However, the industry still lacks a reliable and general way to accurately estimate final shape. This paper demonstrates that the neural network approach is promising to estimate post-HIP dimensions from a combination of pre-HIP dimensions, powder characteristics and processing information. Compared to nonlinear regression models to estimate shrinkage, the neural network models perform very well. Furthermore, the models described in this paper can be used to find good HIP process settings, such as temperature and pressure, which can reduce operating costs.
UR - http://www.scopus.com/inward/record.url?scp=0038341694&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0038341694&partnerID=8YFLogxK
U2 - 10.1023/A:1022907615088
DO - 10.1023/A:1022907615088
M3 - Article
AN - SCOPUS:0038341694
SN - 0956-5515
VL - 14
SP - 219
EP - 228
JO - Journal of Intelligent Manufacturing
JF - Journal of Intelligent Manufacturing
IS - 2
ER -