Wind speed forecasting is critical to renewable energy generation, agriculture, and disaster prevention. Due to the uncertainty and intermittence of wind, conventional forecasting methods with numerical weather prediction (NWP) models fall short of achieving satisfactorily high accuracy. Post-processing of the predicted results is necessary for enhancing the prediction accuracy. The industry generally employs time-series prediction (TSP) methods for error correction, yet it is time-consuming since repeated modeling is needed if the location changes. Aiming at addressing this problem, this paper discusses the application of a deep learning algorithm in the post-processing period of wind speed prediction. NWP results are utilized as the forecasting basis, and deep learning algorithms are used for minimizing errors. An experimental study is conducted with industrial data. The functionality and performance of TSP-based algorithms including rolling mean, exponential smoothing, and autoregressive integrated moving average algorithms are compared with deep learning-based algorithms, including long-short term memory and convolutional neural network. From the numerical results, both TSP and deep-learning error-correction methods can effectively increase the accuracy of day-level NWP model prediction results, while deep-learning methods are data-driven, and no modeling process is needed. This work also poses an insight into the future development of wind speed prediction in meteorology.
We present a measurement method for obtaining three-dimensional (3-D) images of the thoracic and abdominal body surface during respiration. This method generates a color pattern composed of R, G, and B cosine stripe patterns to obtain a single image-based 3-D measurement. The 3-D wavelet transform is adopted to extract wrapped phases from a stripe image sequence to improve the accuracy of the wrapped phase extraction. Then, a two-frequency temporal phase unwrapping formula is proposed and extended to a multifrequency formula according to the geometric relationship between the wrapped and the unwrapped phase curves, which enhances its anti-interference performance and calculation speed. Simulations and body measurements reveal that the proposed method can effectively measure the 3-D body surface during respiration. By using multiple characteristic parameters, this method overcomes the limitation of only using feature points to represent respiratory movement on the thoracic and abdominal body surface. This method has important applications for tracking respiratory motion during clinical radiotherapy.
The hydrothermal method is a frequently used approach for synthesizing HER electrocatalysts. However, a weak tolerance to high temperature is an intrinsic property of carbon cloth (CC) in most situations, and CC-based catalysts, which require complex technological processes in low-temperature environments, exhibit weak stability and electrochemical performance. Hence, we provide a new solution for these issues. In this work, MoO3-NiSx films of 9H5E-CC catalysts are synthesized, first through electrodeposition to form Ni particles on CC and then through a hydrothermal reaction to reform the reaction. The advantages of this synthetic process include mild reaction conditions and convenient operation. The obtained MoO3-NiSx film presents excellent catalytic activity and stability for HER. MoO3-NiSx film requires only a low overpotential of 142 mV to drive 10 mA cm−2 for HER in 1.0 m KOH, and the obtained 9H5E-CF film only needs 294 mV to achieve 50 mA cm−2 for OER. Remarkably, they also show excellent OER, HER, and full water splitting long-term electrochemical stability, maintaining their performance for at least 72 h. This work can be expanded to provide a new strategy for the fabrication of stable, high-performing electrodes using simple, mild reaction conditions.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)
