G01N2021/95646

Dye and pry process for surface mount technology dual in-line memory module

Embodiments of the invention include a dye and pry process for removing a surface mount technology (SMT) dual in-line memory module (DIMM) from card assemblies. Aspects of the invention include immersing a semiconductor package assembly in a solution comprising dye and placing the immersed semiconductor package assembly under vacuum pressure. Vacuum conditions ensure that the dye solution is pulled into any cracks in the solder formed between the semiconductor package assembly and the SMT DIMM. The package assembly is dried, and a dummy card stock is installed in the SMT DIMM using an epoxy. The SMT DIMM is then removed by applying a force to an exposed cavity between the dummy card stock and the semiconductor package assembly. The semiconductor package assembly and the SMT DIMM can then be inspected for the dye to locate cracks.

Substrate inspection device that inspects application quality of adhesive

A substrate inspection device that is placed on an upstream side of a component mounting machine that mounts an electronic component on solder that is printed on a substrate by a solder printing machine, and that inspects the solder and a thermosetting adhesive applied on the substrate, the substrate inspection device including: an irradiator that irradiates the solder and the adhesive with light; an imaging device that takes an image of the irradiated solder and the irradiated adhesive; and a processor that: generates actual solder position information of a solder group that the electronic component is mounted on based on the image, wherein the solder group includes two or more solders; generates, based on design data or manufacturing data, ideal solder inspection reference information indicating a reference inspection position and/or a reference inspection range of the solder included in the solder group.

FOCUS-LESS INSPECTION APPARATUS AND METHOD

An inspection apparatus may include: a structured-light source configured to sequentially radiate a plurality of structured lights having one phase range; a lens configured to adjust, for each of the plurality of structured lights, optical paths of light beams corresponding to phases of the phase range such that a light beam corresponding to one phase of the phase range arrives at each point of a partial region on an object; an image sensor configured to capture a plurality of reflected lights generated by the structured lights being reflected from the partial region; and a processor configured to acquire a light quantity value of the reflected lights; and derive an angle of the surface by deriving phase values of the reflected lights based on the light quantity value for the reflected lights.

Printed circuit board assembly defect detection

A method comprises obtaining a plurality of 2-dimensional gray scale images of a portion of a printed circuit board assembly. Each 2-dimensional gray scale image corresponds to one of a plurality of parallel planes intersecting the portion of the printed circuit board assembly at respective different locations. The method further comprises converting the plurality of 2-dimensional gray scale images into a color image. Each of the plurality of 2-dimensional gray scale images corresponds to and is used as input for a respective color channel of the color image. The method further comprises analyzing the color image to detect variation in color that indicates a defect; and outputting an alert indicating the defect in response to detecting the variation in color.

Apparatus and method of generating control parameter of screen printer

An apparatus, a recording medium, and a method for generating a control parameter of a screen printer are disclosed. The apparatus includes a memory that stores a simulation model configured to derive predictive inspection information on a printed state of solder paste based on a plurality of control parameters of the screen printer; a communication circuit configured to receive first inspection information on a plurality of solder pastes printed by the screen printer based on a first control parameter, and a processor electrically connected to the memory and the communication circuit. The processor obtains first predictive inspection information by applying the first control parameter to the simulation model, generates a plurality of candidate control parameters based on the first predictive inspection information, determines a plurality of second control parameters among the candidate control parameters, and transmits the plurality of second control parameters to the screen printer via the communication circuit.

INSPECTION DEVICE

An inspection device is such that the inspection device executes a mounting inspection of a component using an inspection image of a board on which the component is mounted and includes an imaging device and an image processing device. The imaging device obtains three monochromatic images of the board in R, G, B. The image processing device sets a board color using brightness values of the three monochromatic images obtained by the imaging device, calculates complementary colors of the board color so set, determines on a color component having a largest brightness value in individual color components of the complementary colors so calculated, and sets the monochromatic image having the color component so determined in the obtained three monochromatic images as the inspection image.

System and method for inspecting fused plastic pipes

A method and apparatus for testing a fuse between two plastic pipes without destroying the fuse is performed in the field. The method and apparatus include a source of X-ray radiation and a scanning plate that has pixels that change state when exposed to this radiation. The source of the X-ray radiation is positioned on one side of the fuse and the scanning plate is positioned on another side so that the x-ray radiation passes through the fuse. The x-ray image from the scanning plate makes visible internal voids, weak fuses, and evidence of movement after the plastic of the fitting/pipes melted and flowed together. With such, the quality of the fitting is evident without cutting or otherwise destroying the fitting and, therefore, only weak or otherwise compromised fittings need be cut and redone.

THREE-DIMENSIONAL MEASUREMENT APPARATUS AND THREE-DIMENSIONAL MEASUREMENT METHOD

A three-dimensional measurement apparatus measures measurement targets placed in a target measurement area on a measurement object. The apparatus includes: a measurement module that: is positioned with respect to the target measurement area, and includes: a first irradiator that irradiates the target measurement area with predetermined light for height measurement; a second irradiator that irradiates the target measurement area with predetermined patterned light for three-dimensional measurement; and an imaging device that takes an image of the target measurement area; and a control device that moves the measurement module in a height direction and successively positions the measurement module at a predetermined height position determined by mapping, and performs, based on image data taken by irradiating the target measurement area with predetermined patterned light, three-dimensional measurement to the measurement targets at the predetermined height position.

METHOD AND APPARATUS FOR TRAINING A CONVOLUTIONAL NEURAL NETWORK TO DETECT DEFECTS
20210334587 · 2021-10-28 · ·

The present application discloses a method of training a convolutional neural network for defect inspection. The method includes collecting a training sample set including multiple solder joint images. A respective one of the multiple solder joint images includes at least one solder joint having one of different types of solder joint defects. The at least one solder joint is located substantially in a pre-defined region of interest (ROI) in a center of the image. The method further includes inputting the training sample set to a convolutional neural network to obtain target feature vectors respectively associated with the multiple solder joint images. Additionally, the method includes adjusting network parameters characterizing the convolutional neural network through a training loss function based on the target feature vectors and pre-labeled defect labels corresponding to different types of solder joint defects. The training loss function includes at least two different loss functions.

Method for inspecting ball grid array-type semiconductor chip package

Disclosed are a method, an apparatus, and a system for inspecting a ball grid array-type semiconductor chip package. A first embodiment of the present invention provides an apparatus for inspecting a semiconductor chip package, the apparatus comprising: a first image acquisition unit for acquiring a reference image using a three-dimensional image of a semiconductor chip serving as a reference, the reference image being obtained by removing a region of interest from the three-dimensional image; a second image acquisition unit for acquiring a two-dimensional image of a semiconductor chip to be inspected; and an image processing unit for deriving an image of a region of interest of the semiconductor chip to be inspected, from the difference between the reference image and the two-dimensional image.