Fault Detection and Isolation of a Pressurized Water Reactor Based on Neural Network and K-Nearest Neighbor

Nuclear power plants (NPPs) are complex dynamic systems with multiple sensors and actuators. The presence of faults in the actuators can deteriorate system’s performance cause serious safety issues. This calls for development fault detection diagnosis isolation such faults. In this study, (FDD) based on neural networks (NN) K-nearest neighbour (KNN) algorithm is applied to a pressurized water reactor (PWR). Fault first determined NN. Second, KNN used classify proposed approach capable classifying variety actuator faults, sensor simultaneous A set simulation results provided demonstrate accuracy FDD method. classifier further compared other machine learning techniques.