A repair welding segment detection method includes generating, based on a result of the inspection determination, shape mismatch data obtained by extracting a shape mismatch portion of the weld bead, dividing the shape mismatch data into N. where N is an integer of 2 or more, equally divided windows in a direction perpendicular to a welding direction of the weld bead, setting a shift region formed by i, where i: an integer of 1 or more, continuous windows among the N windows, separately calculating volumes of (N-i+1) shift regions obtained by shifting one by one the i windows forming the shift region in the welding direction, and determining that a shift region having a volume of a predetermined value or more among the calculated volumes of the (N-i+1) respective shift regions is a defective segment of the weld bead.

An automated system for performing multiple operations on one or more weld joints of a pipe string includes a main controller including a user interface; and a first robotic device that is in communication with the main controller and is configured to controllably travel inside of the pipe string and detect and uniquely identify each weld joint within the pipe string based on a vision-based weld detection module that is executed on a first onboard computer. The vision-based weld detection module provides at least one of: (1) images captured within the pipe string and (2) a live video feed within the pipe string that is displayed on the user interface for allowing a user to review and approve detection of the weld joint, whereupon once the user confirms the approval, the first robotic device automatically positions itself a predefined distance from the detected weld joint and automatically begins to perform at least one operation on the weld joint.

An image processing method, apparatus, and device, and a storage medium relate to the field of artificial intelligence. The method may include: obtaining an image corresponding to a target battery module, the target battery module including N solder joints, and the N solder joints being respectively mapped to N solder joint fields in the image; dividing the image according to the N solder joint fields to obtain N image regions in one-to-one correspondence with the N solder joint fields; calculating image difference information between each pair of adjacent image regions among the N image regions to obtain an image difference information set; and performing fault recognition on the target battery module based on the image difference information set. The accuracy for recognizing a preset fault in a battery module can be improved by the method.

A method of inspecting an electric motor includes scanning an electric motor stator winding with a 2D or 3D camera, acquiring one or more images of a plurality welds between adjacent electrical wires forming the stator winding using the 2D camera, analyzing the one or more acquired images with at least one neural network such that the neural network determines if at least one of the plurality of welds has a weld defect. The at least one neural network is trained and distinguishes between surface discoloration on a surface of the welds and defect discoloration resulting from contamination during welding. Also, the method inspects over 150 welds per electric motor stator winding moving along an assembly line.

In an embodiment, an information processing apparatus relating to soldering of a component onto a substrate is provided. The information processing apparatus includes a determination unit determining, using a machine learning model that outputs an inspection result of a post-reflow inspection from an input of image data based on one or more pre-reflow images, whether or not defectiveness will occur in the post-reflow inspection from the image data based on the pre-reflow images acquired in real time.

A solder joint inspection model training method includes the steps of: training a first identification model according to first sample images to identify a surface-mount device with a solder joint in an image; training a second identification model according to second sample images to identify a surface-mount device without a solder joint in an image; inputting labeled original images to a trained first identification model to output first images; inputting the first images to a trained second identification model to output second images; masking the first images with the second images to generate images with normal solder joints and images with abnormal solder joints; and training a solder joint inspection model based on the images with normal solder joints and the images with abnormal solder joints.

A solder printing 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 on the substrate on which a thermosetting adhesive is applied, the solder printing inspection device including: an irradiator that irradiates the solder with light; an imaging device that takes an image of the irradiated solder; 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; outputs mounting position adjustment information to the component mounting machine.

A system for generating training datasets is provided. The system uses base images to generate a large number of images that include non-defective and defective characteristics. The generated images are then used to train a model that may be used to predict defects in real world images of a manufacturing process.

A substrate inspection apparatus generates, when anomalies of a plurality of second solder pastes among a plurality of first solder pastes printed on a first substrate is detected, at least one image indicating a plurality of second solder pastes with anomalies detected by using an image about a first substrate, applies the at least one image to a machine-learning-based model, acquires a plurality of first values indicating relevance of respective first fault types to the at least one image and a plurality of first images indicating regions associated with one of a plurality of first fault types, determines a plurality of second fault types, which are associated with the plurality of second solder pastes by using the plurality of first values and the plurality of first images, and determines at least one third solder paste, which is associated with the respective second fault types.

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.