Predicting the reactivity pulse values of a TRIGA Nuclear Reactor, a Neural Networks approach

The prediction of reactivity pulse values in a TRIGA (Training, Research, Isotopes, General Atomics) nuclear reactor plays a vital role in ensuring safe and efficient reactor operations. In this project, a neural network model is developed to accurately forecast the reactivity pulse values, leveraging the power of artificial intelligence and deep learning techniques. The project focuses on utilizing historical data related to reactor configurations, experimental conditions, and other relevant parameters collected from a TRIGA nuclear reactor located in Texas. This dataset serves as the foundation for training and evaluating the neural network model. The neural network architecture is designed, incorporating appropriate input layers, hidden layers with activation functions, and an output layer to predict the reactivity pulse values.