ANN Based Sensor and Actuator Fault Detection in Nuclear Reactors

In the nuclear power plants (NPPs), fault detection and diagnosis (FDD) methods are very important to improve the safety and reliability of plants. Researchers have established various FDD methods such as model-based methods, data-driven methods, and signal-based methods. In practical applications, model-based methods are very difficult to achieve. Thus, various data-driven methods and signal- based methods have been applied for monitoring key subsystems in NPPs. In this paper, a brief overview of the Artificial Neural Network (ANN) based FDD method is presented. Simulated data have been generated to train the ANNs as per requirement and to compare with the plant signal during a fault. A technique has been proposed analyzing two sensors data (power sensor and coolant sensor) to determine the sensor and actuator fault in a closed-loop in presence of robust (Proportional-Integral-Derivative) PID controller. Results are produced with credible MATLAB simulation