3results about How to "Proportionally large" patented technology

The utility model relates to the technical field of powder processing, and particularly discloses an ultrafine powder microbead sorting system which comprises a raw material warehouse, a primary grading buffer bin, a primary vertical single-rotor grader, a bag type dust collector I, a secondary vertical single-rotor grader, a cyclone collector, a bag type dust collector II and an ultrafine powder bin which are sequentially communicated in series, the first-stage vertical single-rotor grader is further connected with a primary powder selecting coarse powder bin, the second-stage vertical single-rotor grader is further connected with an ultrafine grading coarse powder bin, and the cyclone collector is further connected with a secondary fine powder bin; according to the fly ash secondary sorting device, fly ash is subjected to secondary sorting, micro-bead products with different mesh numbers are selected through control, large-particle-size powder is conveyed to other procedures to participate in grinding and sorting, small-particle-size powder can replace talcum powder, silica powder, ground calcium carbonate and other filling materials in the coating industry, the application industry of fly ash is widened, and the application range of fly ash is widened. The recycling of the fly ash is improved, the energy consumption is reduced, and meanwhile, the environmental pollution caused by mining is reduced.

The application discloses a face segmentation model training method and a face image segmentation method. The method comprises the following steps: obtaining a training sample set; the training sample set comprises a plurality of sample images; inputting the training sample set into a face segmentation model for encoding processing and decoding processing to obtain a plurality of predicted images; performing Hungarian matching on at least one to-be-segmented face region marked in the plurality of sample images and at least one predicted face region included in the plurality of predicted images to obtain at least one unmatched face region; determining a global loss value based on the plurality of sample images and the plurality of predicted images; determining a local loss value based on the regions of the at least one unmatched face region in the plurality of sample images and the plurality of predicted images; determining a target loss value based on the global loss value and the local loss value; adjusting the parameters of the face segmentation model based on the target loss value until a preset training condition is reached to obtain a trained face segmentation model.

The present application relates to feed sewage residue processing technical field, and disclose a kind of feed sewage residue processing device, including processing cylinder, the top of processing cylinder is equipped with cover plate, can be used to process the waste residue after separation, the bottom of the processing cylinder is provided with drain, the top of the processing cylinder is provided with feed inlet, the inside of the processing cylinder is provided with processing mechanism, by motor drive shaft separation cylinder high-speed rotation, make the feed sewage residue injected into separation cylinder under centrifugal force be forced to move to cylinder wall.Liquid part is lighter in quality, more easily pass through filter port and be thrown out to processing cylinder in centrifugal field, while solid residue is intercepted in separation cylinder inside, substantially shorten solid-liquid separation time, and with the continuous rotation of separation cylinder, by poking plate to realize periodic, reciprocating poking cleaning to multiple filter ports, effectively solve the problem of filter screen easy to block, ensure the continuity and stability of solid-liquid separation process, significantly improve processing efficiency.