Characterization of hole-diameter in thin metallic plates perforated by spherical projectiles using genetic algorithms

Abstract

The empirical and semi-empirical models available in literature for the estimation of hole-diameter in thin metallic plates by the strike of spherical projectile are mostly valid for the data for which these have been developed. This may be partly attributed to the form of the model employed for their development. The behavioural constraints and the limiting conditions are not satisfied by these models. In the present paper, some of the non-dimensional models have been developed that satisfy the behavioural constraints and limiting conditions. The data used in the development of earlier statistical models has been reanalyzed for the development of new models for the characterization of hole-diameter with a view towards seeing whether better characterization is possible. The genetic algorithm coupled with the penalty function method has been used for the constrained optimization of model parameters that result in low errors and high correlation coefficients.

Residual Compressive Strength of High-Strength Concrete Exposed to Elevated Temperatures

“…e models based on the artificial neural network (ANN) have been detailed in several studies [92][93][94][95][96][97][98][99]. e main idea of ANN models originates from forming a mathematical relation between the dependent and independent variables by training the models using available data [94][95][96].…”

“…e network architecture of ANN contains twelve neurons and one hidden layer. e tansig transfer function was employed along with the back propagation (BP) formulation [92][93][94].…”

“…It is worth mentioning here that ideal distribution of data between testing/validation and training does not exist. However, a review of literature shows that the percentage of data used for training varies from 67% to 90%, and the remaining data are used for validation and testing [89][90][91][92][93][94][95]. In the present study, the training was done using 2/3rd of the data, whereas the validation and testing were performed using the remaining 33% data [92,93].…”

Optimizing Thermal Shock Resistance of Layered Refractories

“…[18] In this study the fittest parent and the three fittest children are selected to generate the sub-group. [18] In this study the fittest parent and the three fittest children are selected to generate the sub-group.…”