Welding control device, welding control method, and welding control program
US-2021114131-A1 · Apr 22, 2021 · US
US12558735B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-12558735-B2 |
| Application number | US-202017439654-A |
| Country | US |
| Kind code | B2 |
| Filing date | Feb 12, 2020 |
| Priority date | May 8, 2019 |
| Publication date | Feb 24, 2026 |
| Grant date | Feb 24, 2026 |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
A welding control device configured to control a position control object which includes at least one of a welding wire used to weld a welding object or an electrode for melting the welding wire includes a first decision unit for deciding an actual position of the position control object based on a welding feature amount detected from an image which is shot to include at least the position control object, a second decision unit for deciding a target position which is a target of the actual position according to an input condition based on the input condition which includes at least one of attitude information of the electrode when the welding object is welded or shape information of the welding object, and a control unit for performing position control of the position control object so that the actual position becomes the target position.
Opening claim text (preview).
The invention claimed is: 1 . A welding control device configured to control a position control object which includes at least one of a welding wire used to weld a welding object or an electrode for melting the welding wire, the device comprising: a processor; and a non-transitory memory having stored thereon executable instructions, which when executed, cause the processor to perform: deciding an actual position of the position control object based on a welding feature amount detected from an image which is shot to include at least the position control object, the welding feature amount including at least one of a wire position of the welding wire or an electrode position of the electrode; acquiring an input condition which includes attitude information of the electrode when the welding object is welded, the attitude information including information on at least one of a torch angle, an inclination angle, or a roll angle for setting an attitude of the electrode; deciding, based on the input condition, a target position which is a target of the actual position according to the input condition; and controlling a position of the position control object so that the actual position becomes the target position, wherein the processor is configured to decide the target position in a current welding cycle according to the input condition based on a relationship between a previous input condition from a previous welding cycle performed before the current welding cycle and a previous position which is the actual position set under the previous input condition. 2 . The welding control device according to claim 1 , wherein the image further includes at least one of a groove of the welding object or a molten pool formed in the groove by melting the welding wire, wherein the welding feature amount further includes at least one of a groove position of the groove or a molten pool position of the molten pool, wherein the actual position includes an actual relative position which is a relative position of at least one of the wire position or the electrode position to the another welding feature amount, and wherein the target position includes a target relative position which is a target of the relative position according to the input condition when the welding object is welded. 3 . The welding control device according to claim 1 , wherein the processor decides the target position according to the input condition by using a learning model which is obtained by machine learning of a plurality of data associating the previous input condition with the previous position set under the previous input condition. 4 . The welding control device according to claim 3 , wherein the input condition further includes shape information of the welding object and a welding condition when the welding object is welded, wherein the learning model includes a first learning model for obtaining a temporary target position according to the welding condition, and a second learning model for obtaining a correction amount for correcting the temporary target position according to at least one of the attitude information of the electrode or the shape information of the welding object, and wherein the processor decides the target position based on the temporary target position and the correction amount. 5 . The welding control device according to claim 1 , wherein the position control object includes the electrode, wherein the input condition further included shape information of the welding object, wherein the shape information of the welding object includes a groove width of the welding object, and wherein the processor decides the target position of the electrode based on at least the groove width. 6 . The welding control device according to claim 5 , wherein the processor estimates the groove width based on the image and a weaving width of the electrode, and the processor decides the target position of the electrode based on the estimated groove width. 7 . The welding control device according to claim 1 , wherein the processor corrects the welding feature amount based on the attitude information of the electrode, and wherein the processor decides the actual position based on the corrected welding feature amount. 8 . The welding control device according to claim 7 , wherein the image further includes a groove of the welding object, wherein the welding feature amount further includes a groove position of the groove, wherein a shooting part for shooting the image sets a shooting direction to shoot the welding object in accordance with an attitude of the electrode, and wherein the processor corrects the groove position based on the attitude information of the electrode, and the processor decides the actual position based on the welding feature amount including the corrected groove position. 9 . The welding control device according to claim 8 , wherein the attitude information includes a roll angle for setting the attitude of the electrode, and wherein the processor corrects the groove position detected from the image, based on a relation of x=y×tan(θr), where θr is the roll angle, y is a length along a welding direction between a predetermined position and the groove position detected from the image, and x is a length in a direction orthogonal to the welding direction between the predetermined position and the groove position detected from the image. 10 . The welding control device according to claim 1 , wherein the input condition further includes a welding condition when the welding object is welded. 11 . The welding control device according to claim 10 , wherein the welding condition includes at least one condition of an electrode current, an electrode voltage, a welding speed, a supply amount of the welding wire per unit time, or a groove width. 12 . The welding control device according to claim 1 , wherein the processor acquires the image from a shooting part for shooting the image, wherein the processor detects the welding feature amount from the image for each predetermined control cycle, and wherein the processor calculates the actual position based on the welding feature amount. 13 . The welding control device according to claim 12 , wherein the processor determines a detected abnormality in the welding feature amount for each control cycle, wherein, in a normal control cycle which is the control cycle determined that the detected abnormality does not occur, the processor calculates the actual position based on the welding feature amount which is detected from the image acquired in the normal control cycle, and wherein, in an abnormal control cycle which is the control cycle determined that the detected abnormality occurs, the processor calculates the actual position based on the welding feature amount which is detected from the image acquired in the normal control cycle before the abnormal control cycle. 14 . The welding control device according to claim 12 , wherein the processor determines a detected abnormality in the welding feature amount for each control cycle, and wherein the processor stops controlling the position control object in the abnormal control cycle which is the control cycle determined that the detected abnormality occurs. 15 . The welding control device according to claim 1 , wherein the processor corrects the decided target position, if a failure event of the welding is detected. 16 . A welding control method configured to control a position control object which includes at least one of a welding wire used to weld a welding obj
Industrial image inspection · CPC title
Training; Learning · CPC title
using sensing means, e.g. optical · CPC title
Machine learning · CPC title
using feature-based methods · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.