ABSTRACT
Isothermal hot compression tests were conducted on Al 2014 + 2 wt% TiB2 composite at different temperatures (300–450°C) and strain rates (0.001–1 s−1). Using the compression test data, an attempt was made to establish the constitutive relationship for the material by employing three different metamodels such as response surface methodology (RSM), genetic algorithm (GA), and artificial neural network (ANN). The capability of these metamodels towards establishing the non-linear constitutive relation between the process parameters such as temperature, strain rate and strain and flow stress has been ascertained using standard statistical parameters, namely, correlation coefficient (R) and average absolute relative error (AARE). A cubic regression equation was suggested by RSM, while 3–15-1 neural network architecture provided a better correlation. The results obtained are presented and discussed here.
KEYWORDS:
Acknowledgments
The authors thank Dr. G Madhusudhan Reddy, Director DMRL for supporting and motivating us to publish the research article. Furthermore, the funding provided by Defence Research and Development Organization (DRDO) to carry out this work is greatly acknowledged.
Disclosure statement
No potential conflict of interest was reported by the author(s).