@article{akins_furlong_kohler_clifford_brady_alsafadi_wu_2024, title={ARTISANS-Artificial Intelligence for Simulation of Advanced Nuclear Systems for Nuclear Fission Technology}, volume={423}, ISSN={["1872-759X"]}, url={https://doi.org/10.1016/j.nucengdes.2024.113170}, DOI={10.1016/j.nucengdes.2024.113170}, abstractNote={The objective of this Technical Opinion Paper (TOP) is to provide an overview of the research topics in the ARTISANS (Artificial Intelligence for Simulation of Advanced Nuclear Systems) research group at the North Carolina State University. We will discuss the connections between our research with the key items outlined in the Virtual Special Issues (VSI) Nuclear Fission Technology (NFT) series. NFT is crucial for the global goal of decarbonization, but as outlined by the VSI framework, significant challenges remain that inhibit NFT profitability. Our research addresses some of these challenges, centered around improving the simulation of complex nuclear systems with Artificial Intelligence and Machine Learning (AI/ML). The ARTISANS group specializes in many aspects of applications of AI/ML to nuclear engineering, whose potential impact on NFT continues to grow as AI/ML technologies improve.}, journal={NUCLEAR ENGINEERING AND DESIGN}, author={Akins, Alexandra and Furlong, Aidan and Kohler, Lauren and Clifford, Jason and Brady, Christopher and Alsafadi, Farah and Wu, Xu}, year={2024}, month={Jul} }
 @article{akins_kultgen_heifetz_2023, title={Anomaly Detection in Liquid Sodium Cold Trap Operation with Multisensory Data Fusion Using Long Short-Term Memory Autoencoder}, volume={16}, ISSN={["1996-1073"]}, DOI={10.3390/en16134965}, abstractNote={Sodium-cooled fast reactors (SFR), which use high temperature fluid near ambient pressure as coolant, are one of the most promising types of GEN IV reactors. One of the unique challenges of SFR operation is purification of high temperature liquid sodium with a cold trap to prevent corrosion and obstructing small orifices. We have developed a deep learning long short-term memory (LSTM) autoencoder for continuous monitoring of a cold trap and detection of operational anomaly. Transient data were obtained from the Mechanisms Engineering Test Loop (METL) liquid sodium facility at Argonne National Laboratory. The cold trap purification at METL is monitored with 31 variables, which are sensors measuring fluid temperatures, pressures and flow rates, and controller signals. Loss-of-coolant type anomaly in the cold trap operation was generated by temporarily choking one of the blowers, which resulted in temperature and flow rate spikes. The input layer of the autoencoder consisted of all the variables involved in monitoring the cold trap. The LSTM autoencoder was trained on the data corresponding to cold trap startup and normal operation regime, with the loss function calculated as the mean absolute error (MAE). The loss during training was determined to follow log-normal density distribution. During monitoring, we investigated a performance of the LSTM autoencoder for different loss threshold values, set at a progressively increasing number of standard deviations from the mean. The anomaly signal in the data was gradually attenuated, while preserving the noise of the original time series, so that the signal-to-noise ratio (SNR) averaged across all sensors decreased below unity. Results demonstrate detection of anomalies with sensor-averaged SNR < 1.}, number={13}, journal={ENERGIES}, author={Akins, Alexandra and Kultgen, Derek and Heifetz, Alexander}, year={2023}, month={Jul} }