Fatigue Focused Optimization of Treatment Parameters – A Case Study about Deep Cryogenic Treatment

Abstract:

The problem of treatment parameter optimization focused on the fatigue resistance is analysed through a case study about Deep Cryogenic Treatment (DCT) of AISI 302 steel. In particular, the possibility to integrate fatigue data fittings through the Maximum Likelihood Estimation (MLE) method in the optimization process is evaluated. Two levels of two parameters (soaking time and temperature) are considered and then expanded to three by proper scaling of their values in order to include the untreated case as a “zero” level. Fatigue focused optimization is then achieved by standard Response Surface Method (RSM) and by MLE with two models for comparison purposes.

• Periodical: Key Engineering Materials (Volumes 488-489)
• Pages: 498-501
• DOI: https://doi.org/10.4028/www.scientific.net/KEM.488-489.498
• Online since: September 2011
• Authors: Paolo Baldissera, Cristiana Delprete
• Keywords: DCT, Fatigue, Genetic Algorithm (GA), Maximum Likelihood, Neural Network (NN), Optimization

References

[1] D.C. Montgomery, Design and analysis of experiments (Wiley, 2008).

[2] R.H. Myers and D.C. Montgomery, Response surface methodology: process and product optimization using designed experiments (Wiley, 2009).

[3] S.N. Sivanandam and S.N. Deepa, Introduction to genetic algorithms (Springer, 2007).

[4] V. V. Kurban, N.L. Yatsenko and V.I. Belyakova, Metallurgist, Vol. 51 (2007), p.3.

[5] D.F. Cook, C.T. Ragsdale and R.L. Major, Eng. App. of Artif. Intell., Vol. 13 (2000), p.391.

[6] J.C. Figueira Pujol and J.M. Andrade Pinto, Int. J. Fatigue, Vol. 33 (2011), p.313.

[7] L. Jing and P. Jwo, Int. J. Fatigue, Vol. 19 (1997), Issue 5, p.415.

[8] L. Goglio and M. Rossetto, Eng. Fract. Mech., Vol. 71 (2004), p.725.

[9] P. Baldissera and C. Delprete, Mater. Des., Vol. 31 (2010), p.4731.