This research presents a GRNN(General regression neural network) approach for modeling the high temperature deformation flow behavior of 316L stainless steel under 800℃, 900℃ and 1000℃ and strain rates of 0.0002/s, 0.002/s and 0.02/s. There are many machine learning approaches of modeling the hot deformation of metallic alloys. Among them, the neural network approach is one of the most popular. However, the neural network approach takes a relatively long time and effort to compose and optimize the final model. In this research, GRNN is applied to study its applicability for modeling the hot deformation flow stress behavior. The prediction results were studied by calculating various types of error and observing the distribution of prediction error. The predicted results by the GRNN were very accurate and the GRNN was found to be highly applicable to modeling the flow stress of the hot deformation of 316L stainless steel.

In this paper, we have considered the modeling and analyses of categorical data. We modeled binary data with categorical predictors, using logistic regression to develop a statistical method. We found that ANOVA-type analyses often performed unsatisfactory, even when using arcsine-square-root transformations. We concluded that such methods are not appropriate, especially in cases where the fractions were close to 0 or 1. The logistic transformation of fraction data could be a promising alternative, but it is not desirable in the statistical sense. The major purpose of this paper is to demonstrate that logistic regression with an ANOVA-model like parameterization aids our understanding and provides a somewhat different, but sound, statistical background. We examined a simple real-world example to show that we can efficiently test the significance of regression parameters, look for interactions, estimate confidence intervals, and calculate the difference between the mean values of the referent and experimental subgroups. This paper demonstrates that precise confidence interval estimates can be obtained using the proposed ANOVA-model like approach. The method discussed here can be extended to any type of fraction data analysis, particularly for experimental design.