A peening method which can sufficiently improve fatigue properties of a lap fillet welded joint having a thin steel sheet as a base sheet, in which a knocking pin having a predetermined shape is continuously knocked as a series of knocking toward a direction inclined relative to the welding direction, the series of knocking is repeatedly performed in the welding direction, at that time, a knocking mark group made of a plurality of knocking marks formed by the series of knocking is superimposed on at least a part of an adjacent knocking mark group while an end part in the direction orthogonal to the welding direction of the knocking mark group is separated from an end part in the direction orthogonal to the welding direction of the adjacent knocking mark group.

A machine learning device performs machine learning on a laser machine including a plurality of galvanometer mirrors for reflection of a laser beam and a plurality of galvanometer motors for driving the galvanometer mirrors to rotate, and scanning the laser beam over a workpiece. The machine learning device includes: input data acquisition unit that acquires at least two detected temperatures from the galvanometer mirrors and the galvanometer motors as input data; label acquisition unit that acquires a coefficient as a label for calculating a machining target position from an actual position of machining with the laser beam on the workpiece; and learning unit that performs supervised learning using a set of the label and the input data as training data to construct a mathematical model for calculating the machining target position from the actual machining position on the workpiece based on the at least two detected temperatures.

An automated welding system includes a camera for capturing a camera image of a molten pool and an arc generated in a groove by arc welding; an estimation unit for outputting a probability distribution image based on a camera image by using a learned model; an extraction unit for extracting a region having at least a predetermined probability from the probability distribution image; a selection unit for selecting a representative point corresponding to a feature point of an arc and a representative point corresponding to a feature point of a molten pool, in the region having at least the predetermined probability; and a correction unit for correcting a control parameter of a welding robot based on a positional relationship of the representative point corresponding to the feature point of the arc and the representative point corresponding to the feature point of the molten pool.

System and methods for using analytics and algorithms to predict weld quality are provided and include a computer having a processor and memory configured to receive weld parameter data generated during a welding process by a welder to join at least two parts with a weld, input the received weld parameter data to a data analytics model to generate at least one predicted weld quality parameter, compare the predicted weld quality parameter with a weld quality parameter threshold, and generate output indicating at least one of: the at least one predicted weld quality parameter and a result of the comparison between the at least one predicted weld quality parameter and the weld quality parameter threshold

A system and method of electric arc welding that includes a welding apparatus having an electric arc welder torch with sensors to determine the absolute position of the torch tip and the relative position of the torch tip to the weld joint during automatic welding. Combining absolute and relative positional data can be used to adjust the path of the robot during automated or robotic welding in response to variations in the weld joint.

An apparatus for predicting and/or reducing a deformation of an assembly brought about during production of a weld seam that connects a first component and a second component of the assembly includes a device that is configured to determine and/or provide a finite element (FE) model of the assembly where the FE model includes a set of FEs for the weld seam and a set of FEs for the first component and the second component. The device is further configured to induce a spatial contraction of the set of FEs for the weld seam, determine an effect of the spatial contraction on the set of FEs for the first component and/or the second component, and predict a spatial deformation of the first component and/or of the second component on a basis of the effect on the set of FEs for the first component and/or the second component.

Provided is a method for producing a circumferential weld joint. With this method, when low-carbon martensitic stainless steel pipes used for pipelines for transportation of petroleum and natural gas are subjected to circumferential welding, the circumferential welding can be performed efficiently using a low-cost welding material having a composition similar to the composition of the low-carbon martensitic stainless steel pipes. Pipe ends of low-carbon martensitic stainless steel pipes containing prescribed components are butted against each other and subjected to multi-pass arc welding using a welding material containing prescribed components. In the first pass in the multi-pass arc welding, CMT welding is performed in which the welding material is moved back and forth against a molten pool to generate an arc intermittently. In the second and subsequent passes, one selected from GMA welding, GTA welding, and the CMT welding is performed.

A method for monitoring a joining seam, in particular during joining by a laser beam, wherein in the processing direction before a processing point a joining site is measured in order to detect the position and geometry thereof, at least one position of a joining seam is determined from the position of the joining point, and in the processing direction after the processing point the joining seam is measured in order to detect the geometry thereof at the determined position. A device is also provided for carrying out said method and to a laser processing head equipped with such a device.

A weldment that is embedded in a precast concrete building member that is used to join the concrete building member to other concrete building members. The weldment has a top plate, side plate, and outstanding top and bottom legs. The surface of the top plate and side plate are not embedded in the precast concrete building member. The legs are integrally formed with the top plate and side plate. The top plate and side plate present weldable surfaces to join by welding the precast concrete building member to another building member.

A welding method and system (4) using a robotic arm (10), a welding robot (18) and a welding table (2) placed at an angle from horizontal to hold two C-channels (6 and 8) facing each other to maintain position and be welded together. C-channels (6 and 8) face each other to form a closed channel at increased welding speed with less materials having resulting benefits including constant welding, less distortion, and less welding material. Welding begins with restraining C-channels (6 and 8) in conjunction with the angled welding table (2). A robotic arm (10) handles C-channels (6 and 8) to move, place and restrain them relative to each other and the welding table (2). A pressing tool (12) may be a set of pressure-exerting tools (26). A welding robot (18) with a seam finding system (24) preferably welds the restrained C-channels (6 and 8) from top to bottom.