5results about How to "Optimize geometry" patented technology

This invention provides a pre-rotating air inlet ring, a centrifugal fan, and a range hood, belonging to the field of kitchen appliance technology. The pre-rotating air inlet ring includes an outer fixed ring, an inner fixed ring, and multiple blades; the outer and inner fixed rings are concentric and coaxially arranged; multiple blades are distributed between the outer and inner fixed rings, with the inner end of each blade fixedly connected to the inner fixed ring and the outer end fixedly connected to the outer fixed ring; the extension direction of the blades forms an acute angle with the perpendicular line to the axis of the outer fixed ring, i.e., the pre-rotation angle; the annular area is divided into three fan-shaped areas with successively increasing pre-rotation angles (α1<α2<α3) and successively decreasing blade spacing angles (β1>β2>β3). This achieves differentiated and gradient guidance of the inlet airflow in the circumferential direction.

The application discloses a kind of parameterized modeling-based optimization design method and system of centrifugal fan volute profile, belong to industrial centrifugal fan design field.The method includes: firstly, volute profile away from volute tongue side is constructed, determine the width of two circular arcs away from volute tongue side of volute;Second volute tongue profile parameterization constraint, define volute tongue opening degree β, volute tongue radius R, volute tongue center and impeller center distance D key parameter, volute tongue geometry is controlled by three parameters independently;Finally, profile fusion and optimization, adopt single circular arc to connect volute profile away from volute tongue side and volute tongue profile tangentially, avoid geometric over definition problem, complete overall modeling.By improving the degree of freedom of volute tongue area, effectively reduce the flow separation and impeller interference at volute tongue, optimize the uniformity of volute internal flow field.

The present application relates to the field of industrial internet, and provides a federated learning method and system for training of an industrial internet edge sensor device. The method comprises: distributing global model parameters and aggregated momentum to a selected subset of edge sensor devices, and initializing to obtain local model parameters and local momentum; dividing the local model parameters into multiple parameter blocks, performing momentum updating on the current batch gradient through a momentum accumulation algorithm to obtain a momentum matrix; performing orthogonalization processing on the momentum matrix through a Newton-Schulz iteration algorithm to obtain an orthogonalization matrix; performing momentum gradient alignment scoring on the multiple parameter blocks to obtain a smooth alignment score; performing weighted updating on the orthogonalization matrix to obtain updated parameter blocks; and aggregating the parameter block increments and the updated momentum by the server to obtain updated global model parameters and updated global aggregated momentum. The present application reduces the communication frequency and improves the training efficiency of the edge sensor device.

The present application relates to the technical field of turbine blade profile, and discloses a turbine blade geometric parameter optimization method and device and electronic equipment, the method comprises: obtaining the geometric parameter of target turbine blade and the preset parameter of preset turbine blade model;According to the geometric parameter of target turbine, the target blade model of target turbine is generated;According to the geometric parameter of target turbine blade, the target parameter of target blade model and the preset parameter of turbine blade model, the deviation optimization function between the target blade model of target turbine and the preset turbine blade model is generated;According to the deviation optimization function, the geometric parameter of target turbine blade is optimized.The present application does not need manual adjustment of the geometric parameter of turbine blade, but through the deviation optimization function, the geometric parameter of target turbine blade is automatically optimized, and then the geometric parameter of turbine blade is efficiently and accurately optimized.