Power estimation of G.A. Siwabessy Multi-Purpose Reactor at start-up condition using artificial neural network with input variation

Abstract

Thermal power of nuclear reactor needs to be carefully maintained to produce desired electrical power. While in-core measurement system has a higher safety risk, ex-core measurement has been employed to increase safety. Artificial neural network with multi-layer perceptron architecture and Bayesian regularization algorithm has been trained and tested for estimating the thermal power at G.A. Siwabessy multi-purpose reactor. Furthermore, to find out the parameters that provide the strongest influences to thermal power, variations of input were tested to the estimation system. This study found that the output from primary coolant temperature sensor was the main factor that produces the strongest effect toward thermal power of the reactor, whereas the output from pressure sensor providing the smallest effect toward the power calculation.