Selection of radiation shielding material of concrete variety in terms of comprehensive strength and density using ensemble learning algorithms

Selection of exact material for shielding analysis is a challenging task in radiation protection. The primary objective of shielding analysis is to reduce radiation exposure to the occupational worker at their workplace. In general, concrete of high density is selected as the shielding material to prevent the inadvertent exposure from gamma as well as neutron radiation. Composite material or multilayer shielding materials are generally used to optimize the cost of concrete with maximum benefit to the society of occupational radiation workers. Machine learning approach with ensemble learning method is implemented for developing a surrogate model for comprehensive strength of concrete with its other components such as cement, fly ash, coarse and fine aggregates. The underfitting and overfitting issue while fitting a regression model for shielding analysis is taken care by implementing ensemble learning technique of machine learning approach. Comprehensive strength of concrete is mapped to density of the material and observed that higher the density lower is the comprehensive strength. A number of samples of various types of concrete (different composition) is collected as input data and finally a multi attribute decision making method TOPSIS is applied to select appropriate type of concrete. The research work presents the ensemble learning technique and TOPSIS to recommend the exact variety of concrete for shielding of gamma and neutron radiation. (author)