Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

5results about How to "Good shape consistency" patented technology

Flat vacuum cup forming equipment convenient to fix

The utility model discloses flat vacuum cup forming equipment convenient to fix, and relates to the technical field of vacuum cup production. According to the flat vacuum cup forming equipment convenient to fix, by arranging the fixing frame, the fixing blocks, the clamping holes, the clamping blocks, springs, fixing plates, bolts, fixing bases and a long pipe, the function of fixing the long pipe is achieved, the long pipe is prevented from moving in the water swelling process, and therefore a round pipe expands according to a preset shape under the uniform pressure environment; the size precision and the shape consistency of the flat vacuum cup can be improved, and the defective rate of products is reduced; by arranging the fixing base, the connecting rod, the connecting frame, the fixing rod, the connecting ring, the electric telescopic rod, the first adjusting rod, the clamping block and the manufactured long pipe, the function of multiple fixing of the manufactured long pipe is achieved, the fixing function of the manufactured long pipe is further enhanced, and the stable fixing mode can prevent the manufactured long pipe from accidentally moving or popping out in the high-pressure water expansion process.
Owner:ZHEJIANG CAYI HOUSEWARES CO LTD

An integrally formed zipper template

ActiveCN224584300Ugood shape consistencyImprove mechanical properties
This utility model discloses an integrated zipper template, relating to the field of zipper manufacturing technology, including a base plate module, an injection module, a stress dispersion module, and a positioning assembly module. The base plate module is a supporting base plate, and the top surface of the supporting base plate is provided with a matrix-arranged zipper tooth forming cavity group. The zipper tooth forming cavity group includes several evenly distributed single zipper tooth cavities and material distribution cavities. The injection module includes an injection plate located above the supporting base plate, and the injection plate has an injection channel inside that communicates with the zipper tooth forming cavity group. The stress dispersion module is embedded inside the supporting base plate. The positioning assembly module includes multiple positioning holes on the top surface of the supporting base plate and multiple assembly protrusions on the bottom surface of the injection plate. Through the matrix-arranged zipper tooth forming cavity group and the tree-branch-shaped injection channel, the molten material is evenly distributed, reducing material shortages or air bubbles, and improving the shape consistency and mechanical properties of the zipper teeth.
Owner:TANBOER

Medical image generation method based on cyclic diffusion and target guided sampling and application

A medical image generation method based on cycle diffusion and target guided sampling, which generates other target modality medical images from existing source modality medical images by cycle diffusion. In the noise prediction network of the diffusion model of the cycle diffusion model, an additional attention mechanism is introduced to fuse the anatomical structure information in the source modality medical image and the current noise image; at the same time, the anatomical structure segmentation network introduces an anatomical structure shape loss. In training the diffusion model, a perceptual priority weighting P2W training strategy is adopted: by adjusting the loss function weight, the diffusion model is made to preferentially learn the global structure of the image at a high noise level and optimize the image details at a low noise level; at the same time, a target guided classifier for the sampling stage is trained. In the sampling stage: first, the latent code is obtained by reverse sampling from the source modality image; then, under the guidance of the classifier, the target modality probability gradient information is used to guide the sampling process, and the generation of the target modality image is completed.
Owner:NANJING TECH UNIV

Production process of a clothing cord adjusting buckle

The present application relates to the field of clothing accessory products, in particular to a production process of a clothing rope belt adjusting buckle, adopting the following mold structure, comprising an upper mold and a lower mold, the upper mold and the lower mold are buckled to form a cavity, a core is arranged at the joint surface of the upper mold and the lower mold, and an extension channel for the core to pass through is arranged between the upper mold and the lower mold; the production process comprises the following steps: a, before the upper mold and the lower mold are closed, each core passes through the extension channel and enters a specified position in the cavity; b, the upper mold and the lower mold are closed, and the core is extruded to fix the position and keep the cavity structure closed; c, mold casting and cooling are performed to fix the shape of the adjusting buckle; d, the core is pulled out of the mold along the extension channel to perform demolding; e, the upper mold and the lower mold are separated to unload, and the adjusting buckle is obtained. The present application solves the problem of high cost of the existing clothing rope belt adjusting buckle.
Owner:JINJIANG YINXIN ZIPPER WEAVING

Polyp segmentation model based on position sensing feature refinement

The invention relates to medical image processing, in particular to a polyp segmentation model based on position perception feature refinement, an encoder and a lightweight backbone network adopting Transform, and is used for extracting multi-scale semantic features. The decoder adopts a symmetric structure to gradually recover spatial resolution, a plurality of position sensing feature refinement modules PFR are embedded in a shallow layer or multiple layers, attention distribution of shallow semantic features is guided through deep semantics so as to compensate and reconstruct local details, and the position sensing feature refinement modules PFR are embedded in the shallow layer or multiple layers; the decoder further comprises a convolutional layer, a context feature module (CFM), a cross-scale information module (CIM) and a semantic attention module (SAM), and adopts a multi-scale supervision strategy to simultaneously supervise multi-layer output so as to improve the detection and segmentation precision of tiny polyps and boundary pixels; according to the technical scheme provided by the invention, the defect that the tiny polyp is difficult to accurately segment in the prior art can be effectively overcome.
Owner:BEIJING TECH & BUSINESS UNIV