journal article·2011-01

Neural networks for critical high temperature component life prediction

R. E. Johnston

Materials Science and Technology· Volume 27· Issue 1
Publisher page

Abstract

The aim of the present research was to subject a well known parametric model and a neural network model to an acid test of extrapolation in order to determine which can produce improved long term creep rupture life predictions for 2·25Cr–1Mo steels. Linear, squared and cubic parametric models were used and the accuracy of the predictions assessed by calculating the mean percentage absolute error. Many different neural network geometries were developed and the accuracy of the predictions was assessed again by calculating the mean percentage absolute error. As the predictions are concerned with the long term rupture life of components, the accuracy below 60 MPa is of the greatest importance. A neural network model with a 2–5–5–1 architecture provided the lowest error for predictions below 60 MPa, compared to other neural networks and the parametric models, and is therefore the optimum model from this study for predictions of long term rupture creep life for a 2·25Cr–1Mo steel.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: High Temperature Alloys and Creep · Fatigue and fracture mechanics · Material Properties and Failure Mechanisms

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

Materials Research Centre, School of Engineering, Swansea University, Swansea SA2 8PP, UK

References (25)

Show source-provided references
1. 10.1007/BF0264554610.1007/BF02645546 ↗
2. 10.1016/S1350-6307(03)00063-310.1016/S1350-6307(03)00063-3 ↗
3. 10.1016/j.ijpvp.2003.12.01010.1016/j.ijpvp.2003.12.010 ↗
4. Evans R. W. and Wilshire B.: Proc. Sem. on ‘Design of high temperature metallic components’ 89–124; 1984 London Elsevier Applied Science Publishers.
5. 10.1023/A:100477052511810.1023/A:1004770525118 ↗
6. Monkman F. C., and Grant N. J.: Proc. ASTM, 1956, 56, 593.
7. 10.1179/02670839977300336710.1179/026708399773003367 ↗
8. Manson S. S. and Haferd A. M.: ‘A linear time-temperature relation for extrapolation of creep and stress-rupture data’ Technical Note 2890 NASA Washington DC USA 1953.
9. Manson S. S. and Muraldihan U.: ‘Analysis of creep rupture data in five multi heat alloys by minimum commitment method using double heat term centring techniques’ Research Project 638-1 EPRI Cs-3171 EPRI Palo Alto CA USA 1983.
10. Trunin I. I. Golobova N. G. and Loginov E. A.: Proc. 4th Int. Symp. on ‘Heat resistant metallic materials’ Mala Fatra Czechoslovakia September 1971 CSSR 168.
11. Larson F. R., and Miller J.: Trans. ASME, 1952, 74, 765–775.
12. 10.1016/S1350-6307(99)00024-210.1016/S1350-6307(99)00024-2 ↗
13. Caubo M. and Bragard A.: ‘Heavy sheet for pressure vessels II – Heat resistance of A542 steel Class 1’; 1980 Brussels Commission of the European Communities.
14. Azzam H.: J. Aerosp. Eng., 1997, 211, (1), 29–38.
15. 10.1016/S0142-1123(98)00071-110.1016/S0142-1123(98)00071-1 ↗
16. 10.1016/S1359-835X(99)00027-510.1016/S1359-835X(99)00027-5 ↗
17. Penny R. K. and Marriott D. L.: ‘Design for creep’ 205; 1995 London Chapman & Hall.10.1007/978-94-011-0561-3 ↗
18. Swingler K.: ‘Applying neural networks: a practical guide’ 3; 1996 London Academic Press Ltd.
19. Picton P.: ‘Introduction to neural networks’ 21; 1994 London Macmillan Press.10.1007/978-1-349-13530-1 ↗
20. Johnson J. and Picton P.: ‘Mechatronics designing intelligent machines. Concepts in artificial intelligence’ 110; 1995 Oxford Butterworth-Heinemann.
21. Khanna T.: ‘Foundations of neural networks’ 42; 1990 Boston MA Addison-Wesley.
22. Hopgood A. A.: ’Knowledge-based systems for engineers and scientists’ 2nd edn 199; 1993 New York CRC Press.
23. Smith M.: ‘Neural networks for statistical modelling’ 43; 1993 New York Van Nostrand Reinhold.
24. National Research Institute for Metals: ‘NRIM creep data sheet’ No. 3B; 1986 Tsukuba National Research Institute for Metals.
25. Yamauchi M. Chuman Y. Nishimura N. and Masuyama F.: ‘A study on Larson–Miller parameter constant for 2·25Cr–1Mo steel creep-rupture data’ in ‘Creep and fatigue: design and life assessment at high temperature’ 511–519; 1996 Bury St Edmunds Mechanical Engineering Publications.