The thermodynamic state variables in superheated region of steam table are not wholy obtained by measurements. This means that steam table contains a little error. In this study small error was artificially added to superheated variables and modeled using neural networks. The results were compared with the analysis using quadratic spline interpolation method. By and large the relative errors of variables by neural networks were sufficiently small and similar to or less than those by quadratic spline interpolation method. It was concluded that neural networks could be one good way of modeling for superheated steam table.

Abstract
 1. 서론
 2. 해석
  2.1 해석 방법
  2.2 노이즈(noise)
  2.3 상태량 선정
 3. 결과 및 검토
 4. 결론
 후기
 References

• 이태환(경남과학기술대학교 메카트로닉스공학과) | Lee Tae-Hwan
• 박진현(경남과학기술대학교 메카트로닉스공학과) | Park Jin-Hyun Corresponding Author