The increasing generation of renewable electrical power, particularly from wind and solar sources, has significantly influenced the national energy and power transmission systems. However, accurate forecasting of wind and photovoltaic (PV) power remains challenging due to the stochastic and highly nonlinear nature of wind speed and solar irradiance. Traditional models often fail to produce accurate power forecasts. To address this challenge, this paper proposes a novel deep learning model based on the Quantile-Transformed Multi-Attention Residual Framework (QT-MARF). The proposed model is built on a Transformer architecture with Residual Net and Multi-Head Attention. QT-MARF utilizes sequential processing through gated residual networks, enabling the model to learn complex patterns and make accurate power forecasts. The model utilizes PV and wind data from Natal, Santa Vitoria, and the Chinese State Grid (CSG). Case studies are conducted to validate the estimation performance of the hybrid models. The proposed QT-MARF demonstrates promising results in terms of accuracy and efficiency, outperforming traditional models in metrics such as Mean Absolute Error (MAE), correlation coefficient (CC), Root Mean Squared Error (RMSE), and R-squared (R2). Comparative analysis with state-of-the-art techniques such as the Inception-embedded attention-based memory fully-connected network (IAMFN) model, CNN-GRU, CNN-LSTM, and RNN highlights the superiority of the proposed model. These findings suggest that the proposed model offers a promising solution for the challenging task of wind and PV power forecasting.

The time-domain inverse technique based on the time-domain rotating equivalent source method has been proposed to localize and quantify rotating sound sources. However, this technique encounters two problems to be addressed: one is the time-consuming process of solving the transcendental equation at each time step, and the other is the difficulty of controlling the instability problem due to the time-varying transfer matrix. In view of that, an improved technique is proposed in this paper to resolve these two problems. In the improved technique, a de-Dopplerization method in the time-domain rotating reference frame is first applied to eliminate the Doppler effect caused by the source rotation in the measured pressure signals, and then the restored pressure signals without the Doppler effect are used as the inputs of the time-domain stationary equivalent source method to locate and quantify sound sources. Compared with the original technique, the improved technique can avoid solving the transcendental equation at each time step, and facilitate the treatment of the instability problem because the transfer matrix does not change with time. Numerical simulation and experimental results show that the improved technique can eliminate the Doppler effect effectively, and then localize and quantify the rotating nonstationary or broadband sources accurately. The results also demonstrate that the improved technique can guarantee a more stable reconstruction and compute more efficiently than the original one.

The flow pattern and transient response of a spinning cylinder partially filled with fluid are investigated in this paper. A two-dimensional finite element model of the fluid domain in the cylinder cavity is developed via the structured tetrahedral element. By using the volume of fluid model, the flow pattern of the liquid is examined numerically. Also, the effects of fluid type, rotating speed, and liquid height on the flow pattern are investigated. Then, the obtained fluid pressure exerted on the inner wall of the cylinder is considered as the input load, and transient dynamic analysis of the spinning liquid-filled cylinder is carried out. Finally, a comprehensive parametric study is conducted to evaluate the effects of liquid type, spinning speed, and fluid height on the dynamical behavior of the system. The results show that these parameters greatly influence the fluid flow pattern and dynamic characteristics of the spinning liquid-filled cylinder system.

<div class="section abstract"><div class="htmlview paragraph">The increasingly severe energy problems and environmental pollution have imposed severe requirements on the fuel saving level of vehicles. The range extender configuration is a tandem structure that has attracted more and more researchers’ attention due to its architectural features and control methods. An intelligent APU operating point adjustment model based on PMP-GWO-Bi-LSTM is proposed in this paper to enhance adaptability to real driving conditions for the traditional optimal strategy. Firstly, a PMP model has been applied into a range extended electric vehicle model from which the optimized power distribution data under several standard driving cycles was recorded as the input to deep learning model. Secondly, a Bi-LSTM model fed by control parameters and power distribution data was established and trained using aforementioned datasets. The aim is to learning the nonlinear regression relationship model between APU control variables and power distribution. Furthermore, the GWO optimization algorithm is introduced to optimize the hyperparameter of Bi-LSTM to speed up the running speed of the model and improve accuracy. Finally, the experiment was conducted using real driving condition data to predict the power distributions. The simulation results show APU overall efficiency improvement by 15.87% whilst fuel consumption improved by 9.42%. The number of hyper parameters such as the iterations and hidden layer units using GWO optimization algorithm is 35.50% and 38.38% less and the training time decreases by 4.61 s, which proves that the model proposed in this paper can achieve good result in real driving conditions.</div></div>

Laminar burning velocity is a crucial characterization parameter in fuel combustion progress. Investigating the combustion properties is significant to improve combustion efficiency. This paper employs a constant volume combustion bomb and high-speed ripple shadow camera technology to explore the influence of equivalence ratios (0.8–1.4) and ammonia energy shares (0%–40%) on the laminar burning velocity of n-dodecane/ammonia mixture at an ambient temperature of 400 K and a pressure of 1 bar. The results illuminated that the unstretched laminar burning velocity of n-dodecane increased from 46 cm/s at ϕ = 0.8 to 61 cm/s at ϕ = 1 and then decreased to 32 cm/s at ϕ = 1.4. When the ammonia energy ratio reaches 40%, the maximum laminar burning velocity experiences a reduction of 44% because the blended ammonia inhibited the formation of H and O radicals based on kinetic analysis in the fast reaction zone. With the increase of ammonia ratio, the Markstein length of mixed burned gas gradually increases. Particularly under a 1.4 equivalent ratio condition, the Markstein length increases from 0.2 mm to 0.8 mm, indicating that ammonia components significantly enhance flame stability. To gain a deeper understanding of the influence mechanisms of laminar burning velocity, a simplified Yao-Otomo (Y-O) model with 92 species and 355 reactions is proposed, coupling the mechanisms of n-dodecane and ammonia. The Y-O model has demonstrated a predictive trend that is consistent with more detailed WUT-NH3 model (176 species and 2839 reactions), and the Y-O model reduces the amount of computation to save calculation time, which has a higher engineering applicability. The turbulent kinetic energy (TKE) induced by premixed fuel in engine cylinders is estimated through comprehensively analyzing the laminar burning velocity and flame thickness characteristics. The findings indicate a 45% reduction in the peak value of TKE as the ammonia energy ratio increases.

This study examines the spray characteristics of biodiesel, diethyl carbonate (DEC), and their mixtures in a common-rail injection system. Using the schlieren method, the spray tip penetration, spray cone angle, spray tip velocity, spray area, and spray liquid core ratio were observed with a high-speed camera. The test results show that the spray pressure and ambient pressure have significant effects on the spray characteristics. Increasing the spray pressure and decreasing the ambient pressure can increase the spray tip penetration, decrease the spray cone angle, and increase the spray area. After the addition of DEC to biodiesel, with increasing the mixing ratio, the viscosity and surface tension of the mixed fuel are reduced, but the density is increased. This increases the spray cone angle and spray area of the mixed fuel, and it reduces the Sauter mean diameter (SMD). The SMD of droplets were calculated, and it was found that DEC30 has the smallest SMD, and it is of the same order as that of diesel. An improved calculation model for the spray tip penetration of the DEC and biodiesel mixture under high injection pressure was obtained by modifying the exponent of an existing model. By comparing the linear relationship between the injection pressure and the spray tip penetration, it was found that the spray tip penetration of DEC10 has the largest increase.