3results about How to "Performance understanding" patented technology

The invention discloses a hardness testing device for cured resin for dental implant molding, and relates to the technical field of resin hardness testing. Comprising a test installation part, a driving butt joint part is installed on the test installation part, and a closed butt joint part is installed on the test installation part; the closed butt joint piece is used for driving the butt joint piece in a negative pressure suction mode. The interior of the driving butt joint piece is used for injecting resin; an adhesive force detection piece is mounted on the test mounting piece; the adhesive force detection piece is used for upwards moving and jacking the cured resin; a middle curing test piece is mounted on the adhesive force detection piece; the grinding control piece can be used for grinding the surface of the resin when the hardness of the resin is detected, so that the detection surface of the resin is vertical to the hardness detection ejector pin, and the accuracy of a detection value is ensured; the problem that an existing cured resin hardness testing device for tooth implantation forming is inconvenient to automatically control a hardness needle to be perpendicular to a resin detection surface during resin hardness detection is solved.

The invention discloses an insulator detection metering device and a use method, the insulator detection metering device comprises a detection table, the top wall of the detection table is provided with a detection bin, the top wall of the detection table is provided with a fixing assembly, the top wall of the fixing assembly is provided with a plurality of insulator bodies in a clamping manner, and the inner wall of the detection bin is provided with a temperature control assembly. The top wall of the detection bin is provided with a detection assembly. The invention relates to the technical field of insulator detection. According to the insulator detection and metering device and the use method thereof, through mutual cooperation of all parts in the detection assembly, compression resistance detection, internal damage detection and height measurement can be carried out on a plurality of insulators, the overall detection and metering functionality is wide, the overall test efficiency is high, the required time is short, and the detection and metering efficiency is high. And large-batch insulator detection can be carried out.

The application provides a deep learning model security evaluation system and method, comprising the following steps: S1, collecting information of a to-be-tested model and performing pretreatment; S2, testing the to-be-tested model to obtain a test result; the test comprises adversarial attack test, data poisoning robustness test and backdoor trigger reverse test; S3, summarizing all test results and performing analysis to output a final evaluation result. The application provides security analysis for a trainer of a deep learning model, realizes integration of various attack algorithms, including adversarial sample attack, backdoor attack and data poisoning attack, etc., analyzes performances before and after model attack and defense, enables a user to clearly understand performance changes of the user's model under various attack types, and enables the user to comprehensively evaluate the user's model on a unified platform and better grasp security of the model.