Neural Computing Approach to Shape Change Estimation in Hot Isostatic Pressing

  • Orhan Dengiz
  • Abdullah Konak
  • Sadan Kulturel-Konak
  • Alice E. Smith
  • Ian Nettleship
Conference paper


A neural network approach is presented for the estimation of shape change during a Hot Isostatic Pressing (HIP) process of nickel-based superalloys for near net-shape manufacture. For the HIP process, shrinkage must be estimated accurately; otherwise, the finished piece will need excessive machining and expensive nickelbased alloy powder will be wasted (if overestimated) or the part will be scrapped (if 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 a neural network approach is promising to estimate post-HIP dimensions from a combination of pre-HIP dimensions, powder characteristics and processing information.


Neural Network Approach Solid Cylinder Shape Distortion Container Dimension Validation Network 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Atkinson HV, Rickinson B A, (1991) Hot Isostatic Processing. Galliard Printers Ltd., Norfolk, UK.Google Scholar
  2. 2.
    Cherian RP, Smith LN, Midha PS, (2000) A neural network approach for selection of powder metallurgy materials and process parameters. Artificial Intelligence in Engineering, 14 39–44.CrossRefGoogle Scholar
  3. 3.
    Kalpakjian S, (1995) Manufacturing Engineering and Technology. Addison-Wesley Publishing Company, Inc.Google Scholar
  4. 4.
    Khazami-Zadeh M, Petzoldt F, (1995) Hot isostatic pressing of near net shape parts through finite element simulation, Advances in Powder Metallurgy and Particulate Materials Proceedings of the 1995 International Conference & Exhibition on Powder Metallurgy & Particulate Materials. 2:5/125–5/138.Google Scholar
  5. 5.
    MPIF, (2001), web site: <>.
  6. 6.
    NCEMT, (2001), web site: <>.
  7. 7.
    Nissen A, Jaktlund L-L, Tegman R, Garvare, T, (1989) Rapid computerized modeling of the final shape of HIPed axisymmetric containers. Proceedings of Second International Conference on Hot Isostatic Pressing: Theory and Applications, 55–61.Google Scholar
  8. 8.
    Smith LN, Midha PS, (1999) A knowledge based system for optimum and concurrent design, and manufacture by powder metallurgy technology. Internationaljournal of Production Research, 37(1): 125–137.MATHCrossRefGoogle Scholar
  9. 9.
    Twomey JM, Smith AE, (1998) Bias and variance of validation methods for function approximation neural networks under conditions of sparse data. IEEE Transactions on Systems, Man, and Cybernetics, Part C, 28:417–430CrossRefGoogle Scholar
  10. 10.
    Udo GJ, (1992) Neural network applications in manufacturing processes. Computers and Industrial Engineering, 23:97–100.CrossRefGoogle Scholar
  11. 11.
    Wilson RK, Flower HL, Hack GAJ, Isobe S, (1996) Nickel-base alloys for severe environments. Advanced Materials & Processes, 3:19–22.Google Scholar
  12. 12.
    Zhang H-C, Huang SH, (1995) Applications of neural networks in manufacturing: A state-of-the-art survey. International Journal of Production Research, 33:705–728.MATHCrossRefGoogle Scholar

Copyright information

© Springer-Verlag London 2002

Authors and Affiliations

  1. 1.Department of Industrial and Systems EngineeringAuburn UniversityAuburnUSA
  2. 2.Department of Materials Science and EngineeringUniversity of PittsburghPittsburghUSA

Personalised recommendations