Effectively monitoring the operational status of reactor coolant pumps (RCPs) is crucial for enhancing the safety and stability of nuclear power operations. To address the challenges of limited interpretability and suboptimal detection performance in existing methods for detecting abnormal operating states of RCPs, this paper proposes an interpretable, unsupervised anomaly detection approach. This innovative method designs a framework that combines Kernel Self-Organizing Map (Kernel SOM) clustering with Bayesian Posterior Inference. Specifically, the proposed method uses Kernel SOM to extract typical patterns from normal operation data. Subsequently, a distance probability distribution model reflecting the data distribution structure within each cluster is constructed, providing a robust tool for data distribution analysis for anomaly detection. Finally, based on prior knowledge, such as distance probability distribution, the Bayesian Posterior Inference is employed to infer the probability of the equipment being in a normal state. By constructing distribution models that reflect data distribution structures and combining them with posterior inference, this approach realizes the traceability and interpretability of the anomaly detection process, improving the transparency of anomaly detection and enabling operators to understand the decision logic and the analysis of the causes of anomalous occurrences. Verification via real-world operational data demonstrates the method’s superior effectiveness. This work offers a highly interpretable solution for RCP anomaly detection, with significant implications for safety-critical applications in the nuclear energy sector.
In the multiple sequences spread spectrum (MSSS) system, multiple cyclic shifted spreading sequences are superimposed to increase the data rate. This paper proposes a dual-mode MSSS system with index modulation aided by a secondary pilot symbol (DM-MSSS-IM) for underwater acoustic communication. The proposed system divides the bit stream into index bits and modulated bits. The modulated bits are mapped to dual-mode constellations. The index bits are used to select a place for the first modulation mode symbol. The unselected place is used to carry the second mode symbols, which is regarded as the secondary pilot symbol (SPS) to enhance channel estimation. The simulation results show that the proposed system achieves a higher data rate than the existing MSSS system over time-frequency doubly selective fading channels and underwater acoustic channels as the cost of a slight BER performance loss. Additionally, the field experiment verifies the superiority of the proposed scheme.
1 November 2022 in Journal of Physics: Conference Series
As the backbone Grid for STATE GRID Corporation of China, UHV projects require high safety and reliability. 1000kV GIS switchgear is the most important part of UHV AC substation. Deepening the research on its layout and improving the safety and stability can provide strong technical support for the subsequent UHV AC project construction, which is of great significance. The defect and failure rate of indoor GIS is lower than that of outdoor GIS, but the initial cost of indoor GIS is higher than that of outdoor GIS layout scheme. According to the operation related data, this paper carries out the design scheme research, technical scheme comparison and life cycle analysis of indoor and outdoor layout of 1000kV GIS equipment.
The joint source-channel coding (JSCC) scheme consisted of double protograph low-density parity-check (DP-LDPC) codes and was optimized in recent years, but there is still a lack of effective optimization algorithms for the edge connection matrix B L2 . In this paper, through the analysis of adding edge connections at different positions of the edge connection matrix in B L2 and calculating the decoding threshold, it is concluded that adding edge connections will not necessarily improve the waterfall and the error floor of the JSCC scheme. Since the system performance improvement by adding edge connections in B L2 is limited, a novel efficient algorithm with minimum cost is proposed based on a differential evolutionary algorithm. Simulation results and joint protograph extrinsic information transfer (JPEXIT) calculated value have shown that the performance of the algorithm is effectively optimized for the edge connections in B L2 .