When using the Transformer model for wind power prediction, the presence of noise in wind power data and the model’s final layer relying solely on a simple linear output reduces the model’s ability to capture nonlinear relationships, leading to a decrease in prediction accuracy. To address these issues, this paper proposes an ultrashort-term wind power prediction model based on exponential weighted moving average (EWMA) data processing and Kolmogorov–Arnold Network (KAN)-Transformer. First, multiple variable features are smoothed using EWMA, which suppresses noise while preserving the original data trends. Then, the EWMA-processed data is input into the Encoder and Decoder modules of the Transformer model to extract features. The output from the Decoder layer is then passed through the KAN layer, built using a cubic B-spline function, to enhance the model’s ability to capture nonlinear relationships, thereby improving the prediction accuracy of the Transformer model for wind power. Finally, experimental analysis is conducted, and it shows that the proposed model achieves the highest prediction accuracy, with a mean absolute error of 4.38 MW, a root mean squared error of 7.37 MW, and a coefficient of determination of 98.73%.

Lithium-ion batteries serve as vital power sources across various industrial sectors, necessitating accurate modeling and state monitoring via battery management systems to ensure reliable and efficient operations. This paper proposes a co-estimation scheme for state-of-charge (SOC) and state-of-health (SOH) using Bayesian inference. First, a fractional-order model (FOM) is introduced to capture battery dynamics due to its capability to describe both time-domain and frequency-domain characteristics. To address the complex parameter identification challenges inherent in FOMs, the paper proposes a Bayesian-optimization-algorithm (BOA) which efficiently reduces computational complexity and time associated with evaluating fractional-order functions. Next, a combination of Gaussian-sum particle filter (GSPF) and recursive total least squares (RTLS) is proposed to simultaneously estimate battery SOC and SOH. The principle of GSPF is to approximate posterior distribution by weighted Gaussian mixtures, which can avoid the time-consuming resample process of sequential-importance-resample PF while retaining its advantages. The RLTS can fully consider biased noises of SOC estimation and accumulated ampere hour measurements. Additionally, the co-estimation algorithm provides accurate estimates of crucial battery aging parameters such as capacity and internal resistance, facilitating enhanced model adaptation and estimation accuracy over the battery’s entire lifespan. Finally, the proposed method is compared with several available technologies to highlight its superiorities in terms of accuracy, complexity, and robustness.

When using the Transformer model for wind power prediction, the accuracy of the model predictions tends to be reduced due to the shift in the wind power data distribution, channel mixing, and the inability of the model to establish strong correlations. To address these challenges, this paper proposes an ultra-short-term wind power prediction model based on the DT-DSCTransformer. First, the model applies DT’s self-learning standardization and de-standardization parameters to standardize the input and de-standardize the output, mitigating the impact forecasting of data distribution shifts on prediction accuracy. Second, the proposed De-Stationary Channel Attention (DSCAttention) mechanism is introduced. By incorporating De-Stationary Attention (DSAttention) into the channel attention mechanism while maintaining channel independence, the model establishes stronger inter-channel correlations, addressing the performance degradation caused by channel mixing and weak correlations. Finally, experimental analysis demonstrates that the proposed model achieves the highest prediction accuracy compared to commonly used time series forecasting models.

As onshore space resources become exhausted, the migration of wind turbines to offshore areas is an inevitable trend. The blades of offshore wind turbines are typically over 100 m long, and this increased nonlinearity in the blades escalates the risk of flutter. Addressing the flutter phenomenon in these ultra-long flexible blades, this research establishes a full-scale model (FSM) considering geometric and material nonlinearities to accurately characterize the nonlinear dynamic response. Compared to the equivalent beam model, the proposed FSM better lays a foundation for flutter suppression research. On this basis, a bidirectional TMD was innovatively applied to the wind turbine blade and compared against a unidirectional TMD. The results demonstrate that bidirectional TMD can enhance the flutter control rate of 15 MW blades to over 90%, significantly improving flutter characteristics. Compared to the original blade, the steady-state amplitude is reduced by up to 45.73%, markedly suppressing flutter levels. These findings provide theoretical and data support for subsequent studies on aeroelastic instability and flutter suppression in ultra-long flexible blades, offering significant engineering application value and potential for broader implementation.

With the continuous development of the new energy vehicle industry, in order to further improve the safety and range of electric vehicles, vehicle lightweighting has been a key focus of major car companies. However, research on lightweighting and the impact protection effect of battery pack protective plates is lacking. The bottom protective plate of the battery pack in this study has a sandwich-type multi-layer structure, which is mainly composed of upper and lower glass-fiber-reinforced resin protective layers, steel plate impact resistant layers, and honeycomb buffer layers. In order to study the relationship between the impact damage response and material characteristics of the multi-material battery pack protective plate, a matrix experimental design was adopted in this study to obtain the energy absorption ratio of different material properties when the protective plate is subjected to impact damage. This work innovatively used a low-cost equivalent model method. During the drop hammer impact test, a 6061-T6 aluminum plate in direct contact with the lower part of the bottom guard plate test piece was used to simulate the deformation of the water-cooled plate in practical applications. High-strength aluminum honeycomb was arranged below the aluminum plate to simulate the deformation of the battery cell. This method provides a scientific quantitative standard for evaluating the impact resistance performance of the protective plate. The most preferred specimen in this work had a surface depression deformation of only 8.44 mm after being subjected to a 400 J high-energy impact, while the simulated water-cooled plate had a depression deformation of 4.07 mm. Among them, the high-strength steel plate played the main role in absorbing energy during the impact process, absorbing energy. It can account for about 34.3%, providing reference for further characterizing the impact resistance performance of the protective plate under different working conditions. At the same time, an equivalence analysis of the damage mode between the quasi-static indentation test and the dynamic drop hammer impact test was also conducted. Under the same conditions, the protective effect of the protective plate on impact damage was better than that of static pressure marks. From the perspective of energy absorption, the ratio coefficient of the two was about 1.2~1.3.