B23K31/00

Welding monitoring system

To improve quality control of welding, there is included in resistance welding: a magnetic field measuring unit (205) disposed around a welded part and configured to measure a local current at the welded part; a high-speed camera (202) configured to capture an image for measuring local temperature at the welded part from variation of luminance of emission by capturing light emission state of the welded part; a comparison determination unit (106) configured to determine whether or not at least one of current information and temperature information has an abnormal value by comparing the current information calculated based on magnetic field information acquired from the magnetic field measuring unit with past current information and comparing the temperature information measured from an image of the high-speed camera (202) with past temperature information.

Arc welding display device and display method

An arc welding display device is included in a welding apparatus having a weaving function of swinging a torch with respect to a welding direction. The arc welding display device displays, on a screen, at least one of a welding current and a welding voltage during the arc welding with a range sectioned by each fixed period including at least one weaving period.

Machining condition adjustment device and machine learning device
11318565 · 2022-05-03 · ·

A machining condition adjustment device adjusts settings of an ionizer so as to neutralize a charge carried by plasma generated during laser beam machining of a workpiece by a laser beam machining device, calculates an amount of charge per unit time that is to be radiated from the ionizer, based on the amount of charge carried by the plasma generated during the laser beam machining, and sets the ionizer to radiate the calculated amount of charge per unit time.

Gate opener stand
D0950773 · 2022-05-03 ·

METHOD AND APPARATUS FOR GENERATING ARC IMAGE-BASED WELDING QUALITY INSPECTION MODEL USING DEEP LEARNING AND ARC IMAGE-BASED WELDING QUALITY INSPECTING APPARATUS USING THE SAME

An apparatus for generating arc image-based welding quality inspection model is disclosed. The apparatus includes: a hall sensor for measuring a welding current flowing in a base metal through an arc welding machine; a voltage meter for measuring a welding voltage through a circuit generated between the arc welding machine and the base metal; a camera for capturing an image of a welding target area on which the arc welding machine performs welding; and a model generator configured to: identify a welding state based on the welding current measured using the hall sensor and the welding voltage measured using the voltage meter; obtain an arc image based on the image captured; associate the obtained arc image with a welding quality identified based on the arc image to generate a dataset; and apply the generated dataset to a deep-learning model to generate an arc image-based welding quality inspection model.

Sensor device for welding

The durability and detection accuracy of a sensor unit may possibly decrease due to radiation heat generated from work pieces while they are welded together. A sensor device 1 includes a sensor unit 2, a housing case 3, and a shielding member 5. The sensor unit 2 is a device for measuring the shapes of the work pieces W or the distance to the work pieces W. The housing case 3 houses the sensor unit 2 and has formed therein a pass-through portion 36a for laser beam projection and a pass-through portion 36b for detection that pass a laser beam L1 from a laser beam projection unit 21 and a laser beam L2 directed to a detection unit 22, respectively. The shielding member 5 is attached to the housing case 3, and shields radiation heat directed toward the lower surface of the housing case 3 among radiation heat generated while the work pieces W are welded together. The shielding member 5 is made of a material with lower thermal conductivity than that of the housing case 3.

Device and method for reducing and homogenizing residual stress of a component by array of high-energy elastic waves

A device and method for reducing and homogenizing residual stress of a component by an array of high-energy elastic waves. The device includes a tubular body consisting of at least two elements, multiple first through holes and a clamping device provided on an outer side of the tubular body. Exciters are connected with exciting wedges so that an end face of each of the exciting wedges is closely coupled to a surface of the component. A connection portion is coupled to an emitting end of each of the exciters, where the axis of the emitting end coincides with a normal line at a pressed surface of the component A multi-channel signal amplifier is electrically connected to each of the exciters and a multi-channel excitation control module is electrically connected to the multi-channel signal amplifier.

Non-consumable electrode arc-welding method

A non-consumable electrode arc-welding method is provided for causing a welding machine to output or stop a welding current in accordance with at least an ON state and an OFF state of a start signal. In the method, a start signal is switched between an ON state and an OFF state, thereby controlling the on/off operation of the welding machine. Further, an operation mode instruction signal is switched between a normal mode and an interval mode, thereby controlling the operation mode of the welding machine. When the operation mode instruction signal indicates the interval mode and also the start signal is in the ON state, the welding current is outputted in a welding current output period. Then, the output of the welding current is suspended in a welding current interval period successively following the welding current output period.

SOLDER JOINT INSPECTION MODEL TRAINING METHOD, SOLDER JOINT INSPECTION METHOD, AND SOLDER JOINT INSPECTION DEVICE
20220023977 · 2022-01-27 ·

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.

Relating welding wire to a power source

Embodiments of systems and methods to relate welding wire to a welding power source are disclosed. One embodiment is a networked system having a server computer. The server computer is configured to receive first data including at least one of an identity or a location of a consumable source of welding wire, and at least one of a weight status, indicating a change in weight, or an energization status, indicating an energization state, of the consumable source of welding wire. The server computer is configured to receive second data including at least one of an identity or a location of a welding power source, and an activation status indicating an activation state of the welding power source. The server computer is configured to match the welding power source to the consumable source of welding wire based on at least the first data and the second data.