Photovoltaic power generation prediction constitutes a significant research area within the realm of power system artificial intelligence. Accurate prediction of future photovoltaic output is imperative for the optimal dispatchment and secure operation of the power grid. This study introduces a photovoltaic prediction model, termed ICEEMDAN-Bagging-XGBoost, aimed at enhancing the accuracy of photovoltaic power generation predictions. In this paper, the original photovoltaic power data initially undergo decomposition utilizing the Improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (ICEEMDAN) algorithm, with each intrinsic mode function (IMF) derived from this decomposition subsequently reconstructed into high-frequency, medium-frequency, and low-frequency components. Targeting the high-frequency and medium-frequency components of photovoltaic power, a limiting gradient boosting tree (XGBoost) is employed as the foundational learner in the Bagging parallel ensemble learning method, with the incorporation of a sparrow search algorithm (SSA) to refine the hyperparameters of XGBoost, thereby facilitating more nuanced tracking of the changes in the photovoltaic power’s high-frequency and medium-frequency components. Regarding the low-frequency components, XGBoost-Linear is utilized to enable rapid and precise prediction. In contrast with the conventional superposition reconstruction approach, this study employs XGBoost for the reconstruction of the prediction output’s high-frequency, intermediate-frequency, and low-frequency components. Ultimately, the efficacy of the proposed methodology is substantiated by the empirical operation data from a photovoltaic power station in Hebei Province, China. Relative to integrated and traditional single models, this paper’s model exhibits a markedly enhanced prediction accuracy, thereby offering greater applicational value in scenarios involving short-term photovoltaic power prediction.

While the visible plume from a cooling tower is not a pollutant, it can affect the surrounding environment. Moreover, the accompanied evaporation loss has a great potential for wastewater recovery. In the present study, a novel coupling technology for water conservation and plume abatement was proposed, and its feasibility was verified by using thermodynamic analysis. A surface-type heat exchanger was designed and a thermodynamic calculation model was established. Next, based on the principle of “no plume,” the effect of the number of heat exchanger units (N) and the circulating water volume (G) on the water conservation and plume abatement was evaluated under design condition. Results showed that the optimized parameters for the operation of the cooling towers were N = 8 and G < 3000 m³/h, which have a good effect on water conservation and plume abatement. Furthermore, as per the condensation calculation model, the average water conservation amount was 1.105 kg/s and the annual water conservation amount reached 2.8641 × 10⁷ kg.

An AC excitation power supply will produce a series of harmonic currents in motors compared to the conventional power supply, increase the time harmonic component, and then generate a harmonic magnetic field; harmonics will cause motor vibrations and noise in the motor and will produce a corresponding additional loss, increasing the motor temperature rise; these key technical problems need to be solved in domestic pumped storage AC excitation motor engineering applications. Herein, the no-load loss characteristic test of a 3 MW alternating current excited motor was mainly carried out using a test prototype of the 3 MW alternating current excitation motor. Further, with the aid of the finite element method, the numerical study of the no-load loss characteristics of a 3 MW alternating current excited motor was performed. The relationship between the key factors such as the no-load characteristics, no-load loss characteristics, and constant loss and voltage per unit value is analyzed, and the variation law of the no-load core loss of motors under different loads is explored. The results demonstrate that, under no-load conditions, when the applied voltage was less than the rated voltage, the voltage was proportional to the current. When the applied voltage was more significant than the rated voltage, the current increased as the voltage increased, but the relationship between the two was no longer proportional. The constant loss of the motor maintained a linear relationship with the square of the unit value of the voltage scale. When the square of the unit value of the voltage scale was zero, the loss was equivalent to the wind friction loss under no load. The core loss increased with the increase in load, and the greater the load, the faster the increase rate of the motor iron loss. The comparison deviation between the test and simulation results was less than 10%. The simulation and experimental results verified the effectiveness of finite element modeling and the finite element calculation method.

Cooling towers are widely used in many fields, but the generation of visible plumes has a serious impact on the environment. Moreover, the evaporation losses also cause a great waste of water. In this paper, a vapor-condensing plume abatement system was designed for a mechanical-draft cooling tower based on the mechanism of vapor plume generation. An effective method to achieve water-saving and eliminate the water fog generated in the cooling tower was proposed, and its feasibility was verified by using thermodynamic analysis. Next, the vapor-condensing plume abatement device was designed and used for both the confined space cooling tower (CSCT) and the free space cooling tower (FSCT). The surface type heat exchanger was adopted to design the vapor-condensing plume abatement device. Then a basic calculation flow and method were proposed to obtain thermodynamic operating parameters. According to the comparison between the results of theoretical calculation and practical engineering application, it was found that the designed vapor-condensing plume abatement system obviously benefits the water-saving of a mechanical-draft cooling tower and considerable economic benefits can be obtained. The contents presented provide the theoretical basis and technical support for the upgrade of the cooling tower and the design of the new cooling tower.

The water inlet channel is an essential component of the thermal power plant’s circulating water system. It primarily arranges the water flow in the channel so that it is introduced into the pump room smoothly, steadily, and uniformly. Significantly, the operation state of the circulating water pump is impacted by the flow condition of the water inlet channel. The coal-fired generating set’s water input channel was chosen as the research object in this work, and the Computational Fluid Dynamics (CFD) Method was used to examine hydraulic issues impacting anomalous vibration of circulating pumps. Nine optimization options were also suggested, and the effects of the various plans on the water inlet channel’s flow state were examined—the simulation’s outcomes. The simulation’s findings indicate that the arc deflector can enhance the water entry channel’s flow pattern. The wall-attached bias flow of the suction chamber vanished, and the constant flow state is present around the pump’s bellmouth. The thermal power unit’s circulating water pump’s vibration was eliminated, and the circulating pump’s operating efficiency increased due to the curved deflector’s rectification procedures being implemented in the forebay. The study’s findings can guide the hydraulic performance optimization of channels for water inlets with similar sideways or high slopes.