Nuclear power plants (NPPs) are complex dynamic systems with multiple sensors and actuators. The presence of faults in the actuators and sensors can deteriorate the system's performance and cause serious safety issues. Although concerns about faults in the sensors and actuators in NPPs is a similarly important topic, only a few papers have discussed it. In this study, fault detection and diagnosis (FDD) based on neural networks (NN) and K-nearest neighbour (KNN) is addressed for a pressurized water reactor (PWR). Fault detection is first determined based on the NN. Second, the KNN algorithm is used to classify the faults. The proposed approach is capable of classifying a variety of actuator faults, sensor faults, and multiple simultaneous actuator and sensor faults. A set of simulation results is provided to demonstrate the accuracy of the FDD method. The classifier performance is further compared with other machine learning techniques.INDEX TERMS Fault classification, fault detection, K-nearest neighbor (KNN), neural networks (NNs), nuclear power plants (NPPs), pressurized water reactor (PWR).

This work presents a dynamic neural networkbased (DNN) system identification approach for a pressurized water nuclear reactor. The presented empirical modelling approach describes the DNN structure using differential equations. Local optimization algorithms based on unconstrained Quasi-Newton and interior point approaches are used in the identification process. The efficacy of the proposed approach has been demonstrated by identifying a nuclear reactor core coupled with thermal-hydraulics. DNNs are employed to train the structure and validate it using the nuclear reactor data. The simulation results show that the neural network identified model is sufficiently able to capture the dynamics of the nuclear reactor and it is suitably able to approximate the complex nuclear reactor system.

The present work aims to introduce a nonlinear control scheme that combines intelligent feedback linearization (FBL) and a model predictive control (MPC) for a pressurized water reactor (PWR). The nonlinear plant model that is considered in this study is described by the first-principles approach, and it consists of 38 state variables. First, system identification using a dynamic neural network (DNN) structure is performed to obtain a standard affine nonlinear system. The quasi-Newton algorithm is employed to find the best DNN model. Then, an FBL is formulated to address the nonlinearity of the DNN model. An MPC controller is developed based on the FBL system to improve the system performance. The designed controller is compared with a linear MPC controller that is based on state-space models to evaluate the performance of the proposed controller. The proposed approach improves the load-following operation and offers better disturbance rejection capability than the conventional MPC. In addition, numerical measures are employed to compare and analyse the performances of the two control strategies.

Fault detection and diagnosis (FDD) systems can reduce high costs and energy consumption. This paper presents a machine learning-based fault detection and diagnosis (FDD) technique for actuators and sensors in a pressurized water reactor (PWR). In the proposed FDD framework, faults are first detected using a shallow neural network. Second, fault diagnosis is performed using 15 different classifiers provided in the MATLAB Classification Learner toolbox, including support vector machine (SVM), Knearest neighbor (KNN), and ensemble. Several classifiers were found to provide superior classification performance, including medium KNN, cubic KNN, cosine KNN, weighted KNN, fine Gaussian SVM, quadratic SVM, medium Gaussian SVM, coarse Gaussian, bagged trees, and subspace KNN. The accuracy of the FDD approach was demonstrated using a set of simulation results. INDEX TERMS Fault detection and diagnosis (FDD), nuclear reactor, machine learning, neural networkThis article has been accepted for publication in IEEE Access.

This note presents a nonlinear control approach using dynamic neural network (DNN)-based feedback linearization (FBL) for nuclear reactor power control. The reactor model adopted in this study is based on neutronic dynamic and thermal-hydraulic models. The nonlinear plant is identified by a single-layer DNN trained using Quasi-Newton and Interior-Point methods. The feedback linearization scheme is combined with a Proportional-Integral (P-I) controller and simulations show good performance of the proposed controller. The efficacy of the controller is evaluated in the load-following mode of operation. Moreover, the fault-tolerance performance of the proposed approach is tested.