5results about How to "Easy defect detection" patented technology

The application provides a measuring device, and relates to the technical field of optical detection.The measuring device comprises a support assembly, an auxiliary assembly and a detection mechanism.The support assembly comprises a first support frame and a second support frame arranged oppositely; the auxiliary assembly is arranged on the first support frame; at least one avoiding hole is arranged on a fixed plate in the auxiliary assembly; when a contact is placed on the fixed plate, and a weak boundary area of the contact is arranged opposite to the avoiding hole; the detection mechanism comprises an upper light source assembly, a lower light source and a visual detection assembly; the upper light source assembly and the visual detection assembly are arranged on the second support frame; the upper light source assembly is arranged between the auxiliary assembly and the visual detection assembly; the lower light source is arranged on the first support frame and below the fixed plate; and the light of the lower light source can irradiate to the weak boundary area of the contact through the avoiding hole.The measuring device can improve the image definition when detecting the defects of the contacts of Bluetooth earphones, thereby improving the reliability of the detection result.

The application discloses a kind of defect detection devices for plastic furniture production, it is related to defect detection field, it solves the problem that existing defect detection device is easy to cause incomplete detection, including: detection box and belt conveying frame, the top of belt conveying frame is provided with plastic bucket, the top of plastic bucket is provided with two U-shaped frames, the both ends of U-shaped frame bottom are all installed with first laser probe, and top plate is installed between two U-shaped frames;Further including: detection mechanism, for the inside and outside of plastic bucket synchronous detection, detection mechanism is installed in the inside of detection box, and detection mechanism includes mounting bracket installed in the inside of detection box;The application can make top plate do circular motion in the process of moving downward by detection mechanism, and the inside and outside of plastic bucket can be synchronously detected by the first laser probe at the both ends of U-shaped frame, so as to facilitate the inside and outside of plastic bucket synchronous and fast detection.

Embodiments of the present application disclose a chip verification method and device, system, electronic equipment and storage medium, and relate to the technical field of electronic design automation, which can give full play to the large-scale and rapid verification advantages of a hardware verification platform while facilitating defect detection. The method is based on a hardware verification platform and includes: running a hardware simulation program of a chip to be verified; sending behavior information and behavior result information of the chip to be verified in program running to a software verification platform according to a preset strategy, so that the software verification platform verifies and reviews the chip to be verified according to the behavior information and the behavior result information. The present application is applicable to various chip verifications.

This invention discloses a machine vision-based laser chip surface defect detection device, comprising a chip conveying system, an image acquisition system, and a chip acquisition platform. The chip conveying system transports a waffle box containing chips to the chip acquisition platform. The image acquisition system acquires images of each chip individually. The chip acquisition platform inspects the chips and classifies defective and non-defective chips accordingly. This invention achieves automated surface defect detection of laser chips and filters out defective chips.

The invention discloses a chip abnormal defect identification method based on multi-template fusion and a storage medium. The method comprises the following steps: step 1, constructing a chip defect detection model based on deep learning; step 2, collecting each type of chip image; 3, based on median fusion, obtaining an ideal chip image of each type of chips; step 4, carrying out image difference; step 5, performing sliding cutting on the difference image to obtain chip difference images with the same size and overlapped set sizes; step 6, training a chip defect detection model; step 7, performing differential operation and sliding cutting on the to-be-detected chip image; step 8, predicting a chip defect type and a defect position in a corresponding set chip difference image by using the trained chip defect detection model; and finally, determining the position of the defect in the original to-be-detected chip according to the difference image number of the chip with the set size. According to the invention, the appearance difference between chips of different models can be reduced, the universality of the model is improved, and the defect identification precision is high.