LEARNING MODEL GENERATION METHOD, LEARNING MODEL, AND PROGRAM FOR WELDING INFORMATION, AND WELDING SYSTEM

Title:

LEARNING MODEL GENERATION METHOD, LEARNING MODEL, AND PROGRAM FOR WELDING INFORMATION, AND WELDING SYSTEM

Document Type and Number:

WIPO Patent Application WO/2021/220698

Kind Code:

A1

Abstract:

This learning model generation method is for generating a learning model for learning by taking, as teaching data, image data from a visual sensor and welding information extracted from the image data, wherein: a plurality of welding conditions to be used for generating the learning model correspond to the difference in setting pertaining to at least one item; the image data corresponding to each of the plurality of welding conditions includes at least one of a molten pool, a welding wire, and an arc; the welding information includes at least one of information pertaining to the behavior of the molten pool, information pertaining to the position of the welding wire, and information pertaining to the arc; and the learning model which receives the image data as an input and outputs the welding information is generated.

Inventors:

FURUKAWA NAOHIDE
ISHIZAKI KEITO
KOIKE TAKESHI
KIMURA YUJI
OKAMOTO AKIRA
OZAKI KEITA

Application Number:

PCT/JP2021/013400

Publication Date:

November 04, 2021

Filing Date:

March 29, 2021

Export Citation:

Click for automatic bibliography generation Help

Assignee:

KOBE STEEL LTD (JP)

International Classes:

B23K9/095; G06N20/00

Domestic Patent References:

WO2020039948A1

2020-02-27

Foreign References:

JP2018192524A	2018-12-06
JP2007181871A	2007-07-19
JP2017030014A	2017-02-09
JP2020080006A	2020-05-28

Other References: