Artificial Neural Network Modelling of In-Reactor Diametral Creep of Zr2.5%Nb Pressure Tubes of Indian PHWRs

Abstract A model is developed to predict the in-reactor diametral creep in the Zr–2.5%Nb pressure tube of Indian Pressurized Heavy Water power reactors (PHWR) using Artificial Neural Network (ANN). The inputs of the neural network are alloy composition of the tube (concentration of Nb, O, N and Fe), mechanical properties (YS, UTS, %EL), temperature and fluence whereas diametral creep rate is the output. Measured diametral creep rate data from the sampled pressure tubes operating in Indian PHWRs at Rajasthan Atomic Power Station (RAPS 2), Kakrapar Atomic Power Station (KAPS 2) and Kaiga Generating Station (KGS) are employed to develop the model. A three-layer feed-forward ANN is trained with Levenberg–Marquardt training algorithm. It has been shown that the developed ANN model can efficiently and accurately predict the diametral creep of pressure tube. Results show the high significance of O concentration and mechanical properties in determining diametral creep rate.