Nuclear energy system's behavior and decision making using machine learning

- MASLWR's integral test facilities sensors' were used to train different neural networks for patter recognition.
- Pattern recognition's shows good agreement with the raw data given the high dimensional problem.
- Each of the two events can be easily classified as group sensors have their own footprints.

Early versions of artificial neural networks' ability to learn from data based on multivariable statistics and optimization demanded high computational performance as multiple training iterations are necessary to find an optimal local minimum. The rapid advancements in computational performance, storage capacity, and big data management have allowed machine-learning techniques to improve in the areas of learning speed, non-linear data handling, and complex features identification. Machine-learning techniques have proven successful and been used in the areas of autonomous machines, speech recognition, and natural language processing. Though the application of artificial intelligence in the nuclear engineering domain has been limited, it has accurately predicted desired outcomes in some instances and has proven to be a worthwhile area of research. The objectives of this study are to create neural networks topologies to use Oregon State University's Multi-Application Small Light Water Reactor integrated test facility's data and evaluate its capability of predicting the systems behavior during various core power inputs and a loss of flow accident. This study uses data from multiple sensors, focusing primarily on the reactor pressure vessel and its internal components. As a result, the artificial neural networks are able to predict the behavior of the system with good accuracy in each scenario. Its ability to provide technical data can help decision makers to take actions more rapidly, identify safety issues, or provide an intelligent system with the potential of using pattern recognition for reactor accident identification and classification. Overall, the development and application of neural networks can be promising in the nuclear industry and any product processes that can benefit from utilizing a quick data analysis tool.