ARTIFICIAL NEURAL NETWORK MODELING OF IN-REACTOR AXIAL ELONGATION OF Zr2.5%Nb PRESSURE TUBES AT RAPS 4 PHWR

A model is developed to predict the in-reactor dimensional changes of the pressure tube materials in Indian pressurized heavy water power reactors (PHWRs) using artificial neural networks (ANNs). The inputs of the ANN are the alloy composition of the tube (concentration of Nb, O, N, and Fe), mechanical properties (yield strength, ultimate tensile strength, and percentage elongation), tube thickness, temperature, and fluence whereas axial elongation is the output. Measured elongation data from various tubes used in Indian PHWRs at Rajasthan Atomic Power Station (RAPS 4) are employed to develop the model. A three-layer feed-forward ANN is trained with the Levenberg-Marquardt training algorithm. It has been shown that the developed ANN model can efficiently and accurately predict the axial elongation of pressure tubes. The results show the high significance of Fe concentration and irradiation fluence in determining axial elongation.