In nuclear power systems, centrifugal pumps often need to operate under extreme conditions. However, accurately determining the cavitation status of centrifugal pumps under such extreme conditions is challenging. To improve the recognition accuracy of the three statuses of non-cavitation, incipient cavitation, and severe cavitation while improving the anti-interference capability of the monitoring system, this study extracted cavitation features from centrifugal pumps’ motor current and vibration signals under three different operational conditions. It fused the features using feature-level multi-source information fusion (MSIF) based on the backpropagation neural network (BPNN) or support vector machine (SVM) to construct a cavitation status recognition model and analyzed the results to compare with those of recognition without information fusion. The results show that, compared with one signal source, MSIF can significantly improve the recognition accuracy of cavitation statuses. Combined current and pump casing axial monitoring based on the BPNN is the optimal scheme, with an overall recognition accuracy of 97.3% for all operational conditions, compared to 73.9% for the single current signal and 89.3% for the single casing axial vibration signal. These research results can guide the monitoring of cavitation statuses in practical engineering, as well as timely intervention at incipient cavitations to reduce structural damage to centrifugal pumps and prolong service life.

As a critical component of nuclear power units, the direct cooling water system plays a key role in overall performance. To maintain economic efficiency, it is necessary to adjust the circulating water flow rate as conditions change. Understanding how this system responds dynamically to varying environmental factors—such as seawater temperature and tidal levels—is essential for precise control. While previous studies have explored methods such as variable frequency control, predictive maintenance, and digital twin technologies to optimize system operations, challenges remain in addressing the dynamic response of cooling systems under complex environmental and operational conditions. In this study, the AP1000 was used as the research subject and a comprehensive mathematical model of each part of the cooling water system was built, accounting for delays in processes like pipeline transport. Sensitivity analyses were then carried out to examine how linear disturbances in environmental parameters affect system performance, and how circulating water flow, condenser back pressure, and unit efficiency are interrelated. At the same time, the frequency conversion circulating water pump adaptive adjustment system is used to find the best vacuum conditions according to the change in seawater parameters. The findings offer valuable guidance for enhancing the economic operation of nuclear power plant cooling systems.

Aiming at the mechanical failures of vertical centrifugal pumps generated under the combined effects of centrifugal force and fluid power, which are difficult to be accurately recognized by traditional diagnostic methods, a vertical centrifugal pump fault diagnosis method based on the combination of convolutional neural network (CNN) and bidirectional long and short-term memory neural network (BiLSTM) is proposed. Firstly, a recurrent neural network is introduced on the basis of a convolutional neural network, and a feature extraction and fault classification module is established, which can automatically extract spatial and temporal features from the original input signals and identify the key fault modes. Subsequently, a vertical centrifugal pump fault simulation test rig is built, and the vibration signals of the centrifugal pumps under different faults are collected and used to train the proposed diagnostic model. Finally, the diagnostic models constructed by CNN and BiLSTM are compared with a single CNN diagnostic model for fault identification of vibration signals under different fault conditions. The results of the study show that the accuracy of fault diagnosis reaches 100% by using the technique of multi-channel information fusion, which verifies the advantages of multi-channel data fusion. Moreover, the addition of BiLSTM on the basis of CNN is able to better extract and capture useful information from the time series data. In summary, the method proposed in this study can effectively improve the fault diagnosis accuracy and reliability of vertical centrifugal pumps, providing a feasible technical solution for equipment health monitoring in engineering practice.

Natural draft hybrid cooling (NDHC) for thermal power generating units is proposed to achieve a balance of energy and water consumption for arid areas. This study examines the two main design forms of hybrid cooling with airside in serial and parallel heat exchange based on the same tower shell and heat transfer areas. Taking full consideration of the thermal cycle of the power generating unit, simplified simulation models for different cooling systems are established to show the influences of ambient conditions and marketing factors. Results show that both the hybrid cooling designs have a better cooling efficiency than either dry cooling or wet cooling. Expanded inlet areas of hybrid cooling in the parallel heat exchange design bring high heat transfer performance. As for the serial design, the higher temperature of the air at the outlet of the dry section maintains a larger airside mass flow rate, obtaining a high-efficient cooling system. The hybrid cooling in the serial design type relies more on the heat transfer performance of the wet section and is more sensible to ambient humidity, while the performance of hybrid cooling in the parallel design mainly depends on the dry section and is more easily affected by ambient temperature. Considering the unit cost variations of coal and water treatment, hybrid cooling in the parallel design has a wider range of applications compared with the serial design. With the growth in coal cost, there exist more benefits with the serial design.

The seawater circulation pump represents the pump product with the largest flow rate within nuclear power plants. Its energy consumption accounts for a substantial portion of the energy consumed by nuclear power plants. To investigate the internal flow characteristics of the seawater circulation pump and optimize the performance while reducing energy consumption, taking the seawater circulation pump as the research object, the entropy production of each flow passage component of the pump under different flow conditions are analyzed by employing numerical simulation based on the entropy production theory. Additionally, the entropy production mechanisms of the impeller and volute are specifically analyzed. The results demonstrate that under different flow conditions, the impeller and volute are the main flow components contributing to entropy production losses for the entire pump. The leading and trailing edges of the blade and the shroud are the main locations where entropy production occurs in the impeller. Excessive attack angle and circulation are the main factors leading to entropy production. The throat area of the volute is the main entropy production area of the volute, and the secondary flow and vortex caused by flow separation are the main causes of entropy production.