Anomaly Detection for Self-Powered Neutron Detectors Using the Burnup-Adaptive Spatial-Temporal Model

Self-powered neutron detectors (SPNDs) are critical instruments in nuclear power plants (NPPs), yet their malfunctions may result in misperception and misdiagnoses. Plentiful SPNDs are deployed at various locations and reflect the neutron fluence rate in nuclear reactors, empirically derived spatial correlations via Wasserstein distance. However, existing detection methods seldom consider gradual shifts in data distribution and spatial correlations induced by reactor burnup. Hence, this study proposes an SPND-oriented anomaly detection scheme named the burnup-adaptive spatial-temporal model (BA-STM). The scheme abstracts the SPND topology as a graph structure and utilizes a mix-hop temporal convolutional network (MTCN) to extract spatial-temporal interdependencies among overall SPNDs. To alleviate discrepancies across different burnup stages, BA-STM consists of the adversarial discriminator for driving MTCN to learn domain-invariant spatial-temporal features and the lightweight attention reconstructor for filtering pivotal information in complicated features, further obtaining reconstructed SPND signals and residuals. Through variable-boundary detection (VBD), BA-STM quantifies SPND abnormal behavior based on residual statistics exceeding the variable boundaries, enabling effective detection. Experiments on SPND data from a real-world NPP with simulated anomalies verify that the BA-STM exhibits superior performance, reaching optimal F1 scores of 97.915% and 97.671% for single-SPND anomaly detection as well as 97.741% and 97.067% for multi-SPND anomaly detection.