6results about How to "Improve discrimination efficiency" patented technology

The application provides a pre-tailings discarding mode distinguishing method based on useful mineral dissemination characteristics, and relates to the field of mineral processing. The pre-tailings discarding mode distinguishing method based on useful mineral dissemination characteristics comprises the following steps: preparing a plurality of optical sections from an ore sample; analyzing the optical sections by using an optical microscope and an image analysis technology, and classifying the dissemination characteristics of useful minerals in the optical sections; calculating the average occupancy of local enrichment type in all optical sections, the average occupancy of vein type in all optical sections, and calculating a pre-enrichment proportion Pvalid; comparing the pre-enrichment proportion with a preset threshold value, and if Pvalid is greater than or equal to the preset threshold value, it is determined that the ore sample is suitable for pre-enrichment by using a pre-tailings discarding process. The prediction conclusion of the method of the application is highly consistent with actual industrial test and production data, has the advantage of high accuracy, solves the problem that the pre-discarding effect can only be detected by test, and is beneficial to improving work efficiency and reducing cost.

The invention discloses a financial bill intelligent classification method and device based on artificial intelligence. The method comprises the following steps: receiving a financial bill image; inputting the financial bill image into a pre-trained convolutional neural network model, and outputting a financial bill category; the convolutional neural network model comprises a residual feature encoder and a classifier; the residual error feature encoder is used for extracting a layout topological structure and a landmark pattern of the financial bill image; the classifier is used for determining the type of the financial bill by using the layout topological structure and the landmark pattern; and the landmark pattern reflects the category and authenticity of the financial bill. According to the invention, the accuracy, robustness and efficiency of financial bill distinguishing can be improved.

The application discloses a CRTSII type track slab upwarp stability discrimination method, which comprises the following steps: establishing a two-dimensional numerical calculation model of the CRTSII type track slab; combining different adverse influence factors to form a calculation condition, and calculating the track slab allowable temperature amplitude under the upwarp allowable vector condition of the calculation condition by using the two-dimensional numerical calculation model; establishing a sample database according to the calculation condition and the track slab allowable temperature amplitude, constructing a regression model between the adverse influence factors and the slab body allowable temperature amplitude by using a regression analysis method, and improving the regression model; and judging the CRTSII type track slab upwarp stability according to the improved regression model, the measured value of the adverse influence factors and the actual maximum temperature amplitude of the track slab. The application accurately simulates the adverse influence factors of the CRTSII type track slab, establishes a representative sample database, and improves the accuracy and efficiency of the CRTSII type track slab upwarp stability discrimination through the improved regression model.

The utility model relates to the technical field of notebook computers, and particularly discloses a notebook computer hardware vibration polishing machine which comprises a first elastic mechanism and a second elastic mechanism. The first elastic mechanism is fixedly connected with a first fixed seat; the first fixed seat is sleeved with an electric push rod; the upper end of the electric push rod is fixedly connected with a second fixed seat; the second fixing base is movably connected with a protruding plate. Abrasive materials and hardware to be polished are poured into one side space in a polishing containing cavity, then an electric push rod is controlled to stretch, the polishing containing cavity is inclined, then a vibration motor is started, the abrasive materials and the hardware are polished in the polishing containing cavity, and after polishing is completed, the electric push rod is started to lower the height of a polishing container, so that the hardware inclines downwards; the partition plate is matched with the filtering holes to filter out grinding materials, only the hardware is left in the polishing containing cavity on one side, and therefore the function of automatically distinguishing the grinding materials from the hardware is achieved, and the distinguishing efficiency is improved when a large number of small-size hardware is polished.

The application discloses a wide-area low-altitude non-cooperative target real-time discrimination method based on self-supervised incremental learning, and belongs to the technical field of radar target recognition and air traffic surveillance. Firstly, the radar track cluster of the ground-to-air radar and the cooperative target track cluster of ADS-B are acquired, and the neighborhood context spatio-temporal consistency dynamic time warping method is used for hetero-frequency track similarity measurement and cross-threshold nearest neighbor matching. The matching result is used as self-supervised information to construct a discrimination network based on the Transformer Encoder, the robustness is enhanced through random ordering of the track cluster, and the model is evolved autonomously through incremental learning. Finally, combined with GPU parallel computing, end-to-end fast reasoning with a time complexity of O (N) is realized, and the cooperative / non-cooperative attributes of each radar target are output. The application does not need manual labeling, can accurately match hetero-frequency tracks, significantly improves the real-time performance, accuracy and dynamic adaptability of non-cooperative target discrimination, and can be widely deployed in low-altitude traffic control systems.

The invention provides a method for judging a tailing pre-discarding mode based on dissemination characteristics of useful minerals, and relates to the field of mineral processing. The method for judging the tailing pre-discarding mode based on the dissemination characteristics of the useful minerals comprises the following steps: preparing a raw ore sample into a plurality of polished sections; analyzing the X-ray plate by using an optical microscope and an image analysis technology, and classifying the dissemination characteristics of useful minerals in the X-ray plate; calculating the average occupancy of local enrichment types in all the polished sections and the average occupancy of pulse types in all the polished sections, and calculating a pre-enrichment ratio Pvalid; and comparing the pre-enrichment proportion with a preset threshold value, and if the Pvalid is greater than or equal to the preset threshold value, judging that the raw ore sample is suitable for pre-enrichment by adopting a pre-tailing-discarding process. The prediction conclusion of the method is highly matched with the actual industrial test and production data, the method has the advantage of high accuracy, the problem that the pre-polishing effect can only be detected through the test is solved, the working efficiency is improved, and the cost is reduced.