State Power Investment Corporation (China)

As the share of nuclear power plants in the global energy mix increases, ensuring the safety of nuclear power plants has become a crucial task. Existing radiation monitoring technologies face problems such as poor data reliability, difficult data fusion and low accuracy of anomaly detection. In this paper, a machine learning-based method for radiation monitoring data fusion and anomaly identification in nuclear power plants is proposed, which effectively fuses heterogeneous data from multiple sources of multiple sensors by adopting deep learning models such as self-encoder and convolutional neural network (CNN) and improves the accuracy and robustness of the monitoring data. Experimental results show that the method significantly outperforms traditional methods in terms of data fusion accuracy and anomaly detection accuracy, especially when dealing with high-dimensional and complex nonlinear data. Meanwhile, this paper also discusses the challenges faced by deep learning models in practical applications, including computational complexity, model interpretability, and real-time issues. The results validate the great potential of machine learning-based radiation monitoring methods in improving the performance of nuclear power plant safety monitoring systems and provide technical support for building smarter and more reliable monitoring systems in the future.

The fishing-solar complementary (FSC) model, which integrates photovoltaic (PV) power generation with aquaculture, offers a promising approach for China to achieve its dual carbon goals while promoting sustainable fish farming. However, its environmental impacts remain underexplored. This study investigates the Liubao FSC PV station, a national “PV+” pilot project in the Gaoyou Lake area of the Huai River Basin. Combining field data with a water surface energy absorption model, we assess FSC effects on microclimate and aquatic ecology. Key findings include (a) the FSC system raised near-surface air temperature and relative humidity over fishponds by 0.89 ± 0.63 °C and 1.80 ± 2.11%, while reducing wind speed and solar radiation at the water surface by 1.75 ± 0.29 m·s −1 and 63.90 ± 97.19 W·m −2 ; (b) PV panel installation increased surface albedo, reducing net solar energy absorption by 105.76 ± 114.76 W·m −2 ; and (c) water temperature rose by 0.64 ± 0.08 and 0.40 ± 0.06 °C at depths of 0.25 and 0.5 m. Water quality improved, with dissolved oxygen up by 4.09 ± 1.10 mg·l −1 , pH by 0.64 ± 0.12, and chlorophyll a by 167.78 ± 42.95 μg·l −1 , while conductivity, turbidity, and oxidation–reduction potential decreased. The findings of this study provide important practical insights for establishing regional ecological impact assessment frameworks and promoting the coordinated development of the PV and aquaculture industries.

Compared to other energy sources, nuclear power plants (NPPs) can provide clean and reliable electricity with relatively low operating costs. The NPPs are also associated with severe accidents, which are extremely rare. But once they occur, they put immense pressure on the accident management team and may cause great social and environmental impact. In this paper, we report on the ongoing development of an online support system for NPP accident management. This system combined accident diagnosis and online simulation to assess the damage state of NPP, predict possible accident progressions, and evaluate the available actions and their consequences. The system can be equipped in the Technical Support Center (TSC) or the emergency command center (ECC), which can effectively use the data from NPP and communicate with the main control room MCR and other staff immediately.