Advanced methods for loss-of-flow accident precursors identification in a superconducting magnet cryogenic cooling circuit

In nuclear fusion systems, such as ITER, Superconducting Magnets (SMs) will be employed to magnetically confine the plasma. A Superconducting Magnet Cryogenic Cooling Circuit (SMCCC) must keep the SMs at cryogenic temperature to preserve their superconductive properties. Thus, a Loss-Of-Flow Accident (LOFA) in the SMCCC is to be avoided. In this work, a three-step methodology for the prompt identification of LOFA precursors (i.e., those component failures leading to a LOFA) is developed. First, accident scenarios are randomly generated by Monte Carlo sampling of the SMCCC components failures and the corresponding transient system response is simulated by a deterministic thermal-hydraulic code. In this phase, fast-running Proper Orthogonal Decomposition (POD)based Kriging metamodels, adaptively trained to mimic the behavior of the detailed long-running code, are employed to reduce the associated computational burden. Second, the scenarios generated are grouped by a Spectral Clustering (SC) embedding the Fuzzy C-Means (FCM), in order to characterize the principal patterns of system evolution towards abnormal conditions (e.g., a LOFA). Third, an On-line Supervised Spectral Clustering (OSSC) approach is developed to assign signals measured during plant operation to one of the prototypical clusters identified, which may reveal the corresponding LOFA precursors (in terms of combinations of failed SMCCC components). The devised method is applied to the simplified model of a cryogenic cooling circuit of a single module of the ITER Central Solenoid. Results show that the approach developed timely identifies 95% of LOFA events and approximately 80% of the corresponding precursors.