Optimization of thermal neutron shield concrete mixture using artificial neural network

In the present work, Taguchi method and artificial neural network (ANN) were employed to find an optimal mixture of Colemanite based concrete in order to improve the boron content of concrete and increase thermal neutron absorption without violating the standards for physical and mechanical properties. Using Taguchi method for experimental design, 27 concrete samples with different mixtures were fabricated and tested. Water/cement ratio, cement quantity, volume fraction of Colemanite aggregate and silica fume quantity were selected as control factors, and compressive strength, ultrasonic pulse velocity and thermal neutron transmission ratio were considered as the quality responses. Obtained data from 27 experiments were used to train 3 ANNs. Four control factors were utilized as the inputs of 3 ANNs and 3 quality responses were used as the outputs, separately (each ANN for one quality response). After training the ANNs, 1024 different mixtures with different quality responses were predicted. At the final, optimum mixture was obtained among the predicted different mixtures. Results demonstrated that the optimal mixture of thermal neutron shielding concrete has a water-cement ratio of 0.38, cement content of 400 kg/m3, a volume fraction Colemanite aggregate of 50% and silica fume-cement ratio of 0.15.