Provided is image processing unit that causes computer to perform: a spatter candidate region detection step of performing, for each of input images obtained by capturing workpiece during arc welding, detection of a spatter candidate region based on a pixel value indicating brightness of a pixel included in the input images; a reflected light region identification step of identifying, in the spatter candidate region detected in the spatter candidate region detection step, a reflected light region in which reflected light of arc light is shown, based on color information of a reference pixel included in the spatter candidate region; and a spatter number identification step of identifying, as the number of spatters, the number of spatter candidate regions obtained by removing the reflected light region identified in the reflected light region identification step in the spatter candidate region detected in the spatter candidate region detection step.

According to one embodiment, a processing system teaches an operation to a robot. The robot includes a detector including detection elements arranged along first and second directions, and a manipulator to which the detector is mounted. The processing system performs position teaching processing. The position teaching processing includes causing the detector to perform a probe of a weld portion of a joined body. The probe includes a transmission of an ultrasonic wave and a detection of a reflected wave. The position teaching processing includes calculating a center position of the weld portion in a first plane based on first intensity data of an intensity of the reflected wave, setting a teaching point of the robot based on a first position of the detector, and moving the detector along the first plane to a second position, and setting the teaching point based on the second position.

A system for performing computer-assisted image analysis of welds and related methods is disclosed. Digital images are captured at a worksite and sent to a remote image analysis system of a weld analytics system that analyzes images to determine whether the images conform to weld specifications. The remote image analysis system may be trained by artificial intelligence or machine learning.

Provided is a system for detecting a poor weld in a welded portion of a battery module, the system including a battery module fixation unit fixing the battery module to be inspected, an inspection position movement unit moving the battery module fixation unit to a welding inspection position, a welding inspection unit including a frictional reaction force measurement unit inducing a slight movement of the welded portion of the battery module and measuring a frictional reaction force generated thereby and a vision inspection camera detecting an amount of change in a position of the welded portion of the battery module, and a control unit determining whether the welded portion of the battery module is poorly welded based on the frictional reaction force and the amount of position change, measured by the welding inspection unit.

A robotic electric arc welding system includes a welding torch, a welding robot configured to manipulate the welding torch during a welding operation, a robot controller operatively connected to the welding robot to control weaving movements of the welding torch along a weld seam and at a weave frequency and weave period, and a welding power supply operatively connected to the welding torch to control a welding waveform, and operatively connected to the robot controller for communication therewith. The welding power supply is configured to sample a plurality of weld parameters during a sampling period of the welding operation and form an analysis packet, and process the analysis packet to generate a weld quality score, wherein the welding power supply obtains the weave frequency or the weave period and automatically adjusts the sampling period for forming the analysis packet based on the weave frequency or the weave period.

A process for the continuous production of thin-walled, radially closed hollow profiles which are composed of nonferrous metals and have a small cross section comprises supply of a flat strip of the nonferrous metal to a forming apparatus (212) at a first supply speed, where the thickness of the strip corresponds to the wall thickness of the hollow profile. The forming apparatus (212) is configured for continuous forming of the flat strip supplied into a shape corresponding to the hollow profile. After forming, two opposite edges of the flat strip rest flush against one another in a contact region. A welding apparatus (216) continuously welds the edges which rest flush against one another by means of a laser which emits light having a wavelength of less than 600 nm. The laser heats a point in a welding region which has a diameter which is less than 20% of the cross-sectional dimension of the hollow profile. The welded hollow profile is taken off from the welding region, provided in a corrugator (225) with parallel or helical corrugation in sections and taken up in an uptake device (226).

The present invention discloses a control device and method for formation of a weld seam based on frontal visual sensing of a weld pool. In the present disclosure, structural light is adopted to irradiate the concave surface of the weld pool, and a visual sensor is adopted to acquire corresponding structured light images. The weld pool depression feature is acquired through image processing. The welding current is adjusted in real time to maintain the weld pool depression feature constant, and thus the uniform backside width of the weld seam can be acquired to achieve uniform and consistent penetration of the weld seam. The present disclosure only relies on the structural light information on the topside of the weld pool to achieve the control of formation of the weld seam and can be applied to the filler-wire-free DC gas tungsten arc welding of tight butt joints.

A method for inspecting a welding defect of the present invention includes: a threshold resistance setting step (S100) of measuring a resistance of a welded portion of a sample group and deriving a threshold resistance value which becomes an evaluation standard of a weak welding; a resistance measuring step (S200) of measuring a resistance value of a welded portion to be inspected; and a step (S300) of determining as a weak welding if the resistance value measured in the resistance measuring step exceeds the threshold resistance value, wherein the threshold resistance setting step (S100) and the resistance measuring step (S200) include measuring a resistance using a microresistance measuring instrument having a resolution of nanoohm to microohm units.

The welding defect inspection method of the present invention shows excellent detection power for the welding defect by a weak welding.

A non-destructive system for detecting anomalies in weldment of a pipeline is provided including an imaging apparatus, an anomaly detection unit, and a computing device. The imaging apparatus produces image segments corresponding to segments of the circumferential area of the weldment. The anomaly detection unit includes an artificial intelligence platform that processes and analyzes the image segments to identify at least one of a type, size, and location of a welding anomaly within the weldment using a database of truth data. The computing device includes a graphical user interface that displays the image segments with an overlay of information relating to at least one of the type, size, and location of the welding anomaly to the user.

A method for identifying joining positions of workpieces includes capturing images of a joint by a camera, determining measurement data for the joining positions associated with a course of the joint from the images of the joint, determining a mathematical model of the joint course from a part of the measurement data, providing a curve based on the mathematical model for positioning a welding laser during a laser welding process along the curve.