Performance evaluation of neural network topologies for online state estimation and fault detection in pressurized water reactor

• Published in: Annals of nuclear energy 2022-09, Vol.175, p.109235, Article 109235
• Main Authors: Kumar, Swetha R., Devakumar, Jayaprasanth
• Format: Article
• Language: English
• Subjects: Bayesian regularization; Core neutronics; Feed-forward neural networks; NARX neural networks; Recurrent neural networks; Unscented Kalman filter
• ISSN: 0306-4549; 1873-2100
• DOI: 10.1016/j.anucene.2022.109235

•To develop a Neural network model for estimating the internal variables of a pressurized water reactor process and to detect fault at early stage.•Data-driven Neural networks architectures like Feed-Forward Neural networks, Dynamic NARX Neural networks, and Recurrent Neural networks are designed to estimate the reactor core states.•The performance of the selected neural estimator is also compared with the model-based Unscented Kalman filter estimator.•Residuals are generated along with positive and negative threshold using the selected RNN model for fault detection. The nuclear reactor is a multi-rate nonlinear system in which the state variables progress with widely varying dynamics. It has state variables such as reactivity and delayed neutron precursor densities that cannot be measured directly via sensors. Reactivity signifies the criticality of the reactor core. Delayed neutron precursors are the source for delayed neutrons which plays a vital role in the change of neutron densities. Besides, the other states which are measured are also corrupted by measurement noise and are susceptible to sensor faults. Thus, estimation of these state variables becomes critical. As traditional estimators like EKF, UKF, and Particle filers require a close model of the process, Data-driven Neural networks architectures like Feed-Forward Neural networks, Dynamic NARX Neural networks, and Recurrent Neural networks are designed to estimate the reactor core states. The performance of the selected neural estimator is also compared with the Unscented Kalman estimator.