Modelling correlation between hot working parameters and flow stress of IN625 alloy using neural network
Source abstract
Abstract
In this work, an optimum multilayer perceptron neural network is developed to model the correlation between hot working parameters (temperature, strain rate and strain) and flow stress of IN625 alloy. Three variations of standard back propagation algorithm (Broyden, Fletcher, Goldfarb and Shanno quasi-Newton, Levenberg–Marquardt and Bayesian) are applied to train the model. The results show that, in this case, the best performance, minimum error and shortest converging time are achieved by the Levenberg–Marquardt training algorithm. Comparing the predicted values and the experimental values reveals that a well trained network is capable of accurately calculating the flow stress of the alloy as a function of the processing parameters. Sensitivity analysis revealed that temperature has the largest effect on the flow stress of the alloy being in good agreement with the metallurgical fundamentals.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Metallurgy and Material Forming · Mineral Processing and Grinding · Metallurgical Processes and Thermodynamics
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Materials Science and EngineeringSharif University of Technology, Tehran 11365-8639, Iran
References (19)
Show source-provided references
1. Eiselstein H. L., and Tillack D. J. ‘Superalloys 718, 625 & various derivatives’, 1-14; 1991, Warrendale, PA, TMS.10.7449/1991/Superalloys_1991_1_14 ↗
2. Sundararaman M., Mukhopadhayay P., and Baerjee S. ‘Superalloys 718, 625 & various derivatives’, 367-378; 1997, Warrendale, PA, TMS.10.7449/1997/Superalloys_1997_367_378 ↗
3. Floreen S., Fuchs G. E., and Yang W. J. ‘Superalloys 718, 625 & various derivatives’, 13-37; 1994, Warrendale, PA, TMS.10.7449/1994/Superalloys_1994_13_37 ↗
4. Vernot-Loier C., Cortial F.: Superalloys 718, 625 & Various Derivatives, 1991,409–422.10.7449/1991/Superalloys_1991_409_422 ↗
5. 10.1016/S0022-3115(00)00723-610.1016/S0022-3115(00)00723-6 ↗
6. Chang K. M., Lai H. J., and Hwang J. Y. ‘Superalloys 718, 625 & various derivatives’, 683-694; 1994, Warrendale, PA, TMS.10.7449/1994/Superalloys_1994_683_694 ↗
7. Ferrer L., Pieraggi B., and Uginet J. F. ‘Superalloys 718, 625 & various derivatives’, 217-228; 1991, Warrendale, PA, TMS.10.7449/1991/Superalloys_1991_217_228 ↗
8. Kohler M. ‘Superalloys 718, 625 & various derivatives’, 363-374; 1991, Warrendale, PA, TMS.10.7449/1991/Superalloys_1991_363_374 ↗
9. Zhao D., Chaudhury P. K., Frank R. B., and Jakman L. A. ‘Superalloys 718, 625 & various derivatives’, 315-329; 1994, Warrendale, PA, TMS.10.7449/1994/Superalloys_1994_315_329 ↗
10. 10.1007/s11661-000-0147-610.1007/s11661-000-0147-6 ↗
11. 10.1016/j.matdes.2005.07.01810.1016/j.matdes.2005.07.018 ↗
12. 10.1016/j.jallcom.2004.09.01410.1016/j.jallcom.2004.09.014 ↗
13. 10.1016/0893-6080(89)90020-810.1016/0893-6080(89)90020-8 ↗
14. 10.1016/j.matdes.2007.02.00910.1016/j.matdes.2007.02.009 ↗
15. 10.1016/S0927-0256(03)00092-210.1016/S0927-0256(03)00092-2 ↗
16. Haykin S. ‘Neural networks: a comprehensive foundation’; 1999, Upper Saddle River, NJ, Prentice Hall.
17. Guessasma S., and Coddet C.: Acta Mater. 2004, 52, 5157–5164.10.1016/j.actamat.2004.07.022 ↗
18. Koker R. · Mater. Des · 2005 · 28 · 1747
19. 10.1007/s10853-006-1275-110.1007/s10853-006-1275-1 ↗