No abstract

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.

In the International Thermonuclear Experimental Reactor, plasma is magnetically confined with Superconductive Magnets (SMs) that must be maintained at the cryogenic temperature of 4.5 K by one or more Superconducting Magnet Cryogenic Cooling Circuits (SMCCC). To guarantee cooling, Loss-Of-Flow Accidents (LOFAs) in the SMCCC are to be avoided. In this work, we develop a three-step methodology for the prompt detection of LOFA precursors (i.e., those combinations of component failures causing a LOFA). First, we randomly generate accident scenarios by Monte Carlo sampling of the failures of typical SMCCC components and simulate the corresponding transient system response by a deterministic thermal-hydraulic code. In this phase, we also employ quick-running Proper Orthogonal Decomposition (POD)-based Kriging metamodels, adaptively trained to reproduce the output of the long-running code, to decrease the computational time. Second, we group the generated scenarios by a Spectral Clustering (SC) employing the Fuzzy C-Means (FCM), in order to identify the main patterns of system evolution towards abnormal states (e.g., a LOFA). Third, we develop an On-line Supervised Spectral Clustering (OSSC) technique to associate time-varying parameters measured during plant functioning to one of the prototypical groups obtained, which may highlight the related LOFA precursors (in terms of SMCCC components failures). We apply the proposed technique to the simplified model of a cryogenic cooling circuit of a single module of the ITER Central Solenoid Magnet (CSM). The framework developed promptly detects 95% of LOFA events and around 80% of the related precursors.