Hydro energy is a kind of typical renewable energy, which can be converted by hydraulic machinery. However, tip leakage vortex (TLV) has a significant negative influence on the flow pattern and energy performance of hydraulic machinery. In this paper, a bending shrinkage groove (BSG) is proposed to suppress the TLV and improve the energy performance of a hydrofoil first, and then a parametric optimization design method is briefly introduced and applied to determine the optimal configuration of the groove. The main geometric parameters of the groove are selected as optimized variables and three different groove configurations are selected from the optimization result. Finally, the performance improvement of the hydrofoil with groove, the sensitivity analysis of the optimization variables, and the groove impacts on the TLV and flow patterns are investigated. The results demonstrate that the preferred groove reduces the non-dimensional Q criterion vortex isosurfaces area (Qarea = 2 × 107) by 5.13% and increases the lift drag ratio by 17.02%, comparing to the origin hydrofoil. Groove depth d and groove width w are proved to have more significant impacts on the hydrofoil energy performance. The TLV and flow patterns are greatly affected by the different BSG configurations, and the wider BSG contributed to reducing the area of TLV, at the cost of energy performance deterioration.

No abstract

No abstract

Many deep learning methods have been proposed to improve the quality of low‐dose PET images (LPET), which usually construct end‐to‐end networks with certain radiation dose inputs. However, these approaches have omitted the noise disparity in PET images, which may differ among manufacturers or populations. Therefore, we tend to exploit these noise differences among PET images to achieve adaptive restoration. We proposed a 3D noise level‐guided PET restoration network for LPET including (1) adaptive noise level‐aware subnetwork and (2) LPET restoration subnetwork. The first subnetwork aims to predict the noise level of the given LPET, while the second subnetwork treats the estimated noise level as a priori information to guide the restoration process from LPET to standard‐dose PET images. Experiments were performed on real human head and neck datasets while the peak signal‐to‐noise ratio and structural similarity index measure were used to evaluate LPET recovery performance. Moreover, we also compared the proposed network with several deep‐learning approaches. Experimental results demonstrate that our network with dual‐stage design can perform adaptive restoration for LPET, yielding better visual and quantitative results. In future work, we attempt to apply our method to other imaging tasks and adapt it for clinical practice.

No abstract