Precise forecasting of the thermal parameters is a critical factor for the safe operation and fault incipient warning of the ultra‐high voltage (UHV) transformers. In this work, a novel multi‐step forecasting method based on the long‐ and short‐term time‐series network (LSTNet) with the conditional mutual information (CMI) is proposed for the UHV transformer. To improve the computational efficiency and eliminate the redundancy, the CMI‐based feature selection algorithm is applied to analyse the correlation between the original monitoring parameters and construct the optimal feature subset. LSTNet, which is composed of a convolutional layer, recurrent layer and recurrent‐skip layer, is utilized to capture both the short‐term nonlinear characteristics and the long‐term periodic characteristics. The LSTNet model is established to forecast the variation tendency of the oil and winding temperatures for different locations in the UHV transformer. The results show that the proposed method significantly enhances the accuracy in both one‐step and multi‐step thermal parameters forecasting and achieves better performance in terms of the RMSE and MAE compared with other existing methods.

Neutron detectors in nuclear power plants (NPPs) are critical for system stability, yet their malfunctions may lead to false alerts and misdiagnoses. Multidetectors deployed in diverse positions vary with the nuclear reactor states contained spatial-temporal variations of neutron fluxes. Existing methods seldom concurrently consider intricate spatial-temporal correlations and gradual state variations among detectors. This study proposes a detector-oriented fault detection and isolation method named the spatial-temporal state adaptation model (ST-SAM). The method introduces a local-global spatial-temporal network that captures the potential interdependencies within the detector topology. To minimize cross-state discrepancies in reactors, ST-SAM integrates three submodules: a signal reconstructor to enhance the specific-state variation representation; a correlation alignment to mitigate interstate feature discrepancies; and an adversarial discriminator to extract spatial-temporal state-invariant features. Leveraging the parallel detection strategy, ST-SAM effectively detects and isolates faulty detectors, preventing fault propagation on subsequent diagnosis. Experiments on ex-core and in-core neutron detectors in real-world NPPs with simulated faults verify that the ST-SAM outperforms various state-of-the-art methods in terms of signal reconstruction and fault detection.

Balanced in-core power levels in nuclear power plants (NPPs) are critical for safety, whereas power tilt disrupts this balance, reducing safety margins and posing risks.0Early warning for power tilt offers an effective way of optimizing monitoring. Due to abnormal-sample scarcity and security concerns, common data-driven models train on the simulated data generated by simulators. However, achieving a satisfactory effect in practices is difficult because simulators imperfectly emulate reality. Thus, we propose a power tilt-oriented early warning method called simulation-reality spatial-temporal model (SR-STM).0Motivated by the physical model in NPPs, a knowledge-guided hierarchical graph is designed to characterize spatial correlations among local power levels for SR-STM’s input. The SR-STM uses a lightweight spatial-temporal network (LST-Net) as a feature extractor, balancing precision and efficiency. To bridge sim-real inter-domain discrepancies, SR-STM utilizes node-alignment adversarial learning for fine weight tuning in subdomain, and eigenvalue-based scale alignment for sim-real feature proximity. Forecasting local power levels using the SR-STM, dynamic metrics and alarm limits are calculated and compared to perform the early warning task. The online experimental prototype verifies that SR-STM surpasses various state-of-the-art methods in terms of early warning and sim-real cross-domain tasks.

In nuclear power plants (NPPs), ex-core neutron detectors are deployed around reactor cores and are essential for reactor stability, but their deterioration and malfunction can cause misperceptions and misdiagnoses. Existing fault detection seldom accounts for global spatial-temporal coupling relationships implied among overall detectors and uncertainty under transient operations. Thus, we propose a novel detector-oriented fault detection scheme called the global-fused dynamic detection (GFDD) model, established by the global spatial-temporal graph (GSTG), moving-global graph convolution (MGGC), and uncertainty-quantified dynamic detection (UQDD). To enrich informational sources and disperse faulty propagation, we specifically design the GSTG for characterizing the spatial-temporal relationships among overall detectors and the MGGC for efficiently capturing global high-level features, further generating multi-detector reconstructed signals and residuals. Through calculating dynamic statistics and quantifying uncertainty under varying operating conditions, the UQDD identifies faulty detectors and corrects erroneous signals. Experiments on steady and transient states from a real-world NPP with simulated faults validate that the GFDD model outperforms various state-of-the-art methods with regard to signal reconstruction and fault detection.