Yongzhen Gong

To address the challenge of high wind speed variability in wind farm planning, a small-sample-based spatio-temporal fusion and compression deep residual point prediction model, STiCDRS (Spatio-Temporal integration and Compression Deep Residual), is proposed. This model is designed to deeply explore the spatial and temporal characteristics within wind speed sequences to enhance the accuracy of point predictions. Initially, the spatio-temporal integration and compression deep residual network is employed to obtain point prediction results. Subsequently, an innovative hybrid model, STiCDRS-NKDE (STiCDRS-Nonparametric Kernel Density Estimation), is introduced to achieve interval predictions, thereby providing more reliable probabilistic forecasts of wind speed. The hyper-parameters of the model are optimized using Bayesian optimization, ensuring efficient and automated tuning. Finally, a case study involving wind speed forecasting at a wind farm in Inner Mongolia, China, is conducted, comparing the performance of the STiCDRS model with traditional models. Experimental results demonstrate that in comparison to other models, the proposed STiCDRS-NKDE model delivers superior point prediction accuracy, appropriate interval predictions, and reliable probabilistic forecasting outcomes, fully showcasing its significant potential in the domain of wind speed forecasting.

One of the significant factors contributing to high energy consumption is the unutilized waste heat from flue gas in industrial boilers. Thermoelectric generator (TEG) technology can directly convert thermal energy into electrical energy, and has been gradually applied in the field of waste heat recovery due to its simple and reliable structure, environmental protection, and other advantages. In this paper, a thermoelectric generator simulation system of boiler flue gas waste heat is proposed. The experimental platform is designed by simulating the flue gas waste heat temperature condition of boiler, and the structure of cold end module and hot end module is optimized. During the experiment, the fixed temperature difference was set at 120 °C (hot end:150 °C~cold end: 30 °C). An analysis is conducted on the volt-ampere characteristics and output power of the TEG module. The output characteristics of the TEG system are analyzed under the conditions of variable load, constant load, different pump speed, different heat dissipation modes, and series and parallel connection method. The results show that the experimental platform can instantaneously and accurately test the output parameters of the TEG system, and ensure the intended design requirements. When the ratio of the load resistance to the internal resistance of the TEG module is approximately 1–1.15, the output power of the system reaches its maximum. In order to optimize the output power of the TEG system, a power prediction-based adaptive variable step size maximum power point tracking (MPPT) algorithm is introduced. Additionally, a corresponding mathematical model is formulated. Simulations demonstrate that the time of the improved algorithm to reach the stable maximum power point is 1.54 s faster than that of the traditional algorithm. The improved MPPT algorithm satisfies the criteria for speed and accuracy, diminishes superfluous energy waste, and enhances the overall system efficiency. The research results have certain guiding significance for the design and application of subsequent TEG system.

Structural reliability analysis has an inherent contradiction between efficiency and accuracy. The metamodel can significantly reduce the computational cost of reliability analysis by a simpler approximation. Therefore, it is crucial to build a metamodel, which achieves the minimum simulations and accurate estimation for reliability analysis. Aiming at this, an effective adaptive metamodel based on the combination of radial basis function (RBF) model and Monte Carlo simulation (MCS) is proposed. Different shape parameters are first used to generate the weighted prediction variance, and the search for new training samples is guided by the active learning function that achieves a tradeoff of (1) being close enough to limit state function (LSF) to have a high reliability sensitivity; (2) keeping enough distance between the existing samples to avoid a clustering problem; and (3) being in the sensitive region to ensure the effectiveness of the information obtained. The performance of the proposed method for a nonlinear, non-convex, and high dimensional reliability analysis is validated by three numerical cases. The results indicate the high efficiency and accuracy of the proposed method.