Title:
MACHINE LEARNING DEVICE, LAMINATE MOLDING SYSTEM, MACHINE LEARNING METHOD FOR WELDING CONDITION, WELDING CONDITION DETERMINATION METHOD, AND PROGRAM
Document Type and Number:
WIPO Patent Application WO/2022/019013
Kind Code:
A1
Abstract:
A machine learning device for carrying out machine learning of a welding condition when molding a laminate molded object by welding a filler material and laminating a welding bead, said machine learning device having a learning processing means for carrying out a learning process for generating a learned model in which a welding condition for the welding bead and a block pattern formed by the welding bead are set as input data, and shape data for the welding bead is set as output data.
Inventors:
HUANG SHUO
Application Number:
PCT/JP2021/022942
Publication Date:
January 27, 2022
Filing Date:
June 16, 2021
Export Citation:
Assignee:
KOBE STEEL LTD (JP)
International Classes:
B23K31/00; B23K9/032; B23K9/04; B23K9/095; B33Y10/00; B33Y30/00; B33Y50/02
Domestic Patent References:
WO2020079816A1 | 2020-04-23 |
Foreign References:
JP2020006378A | 2020-01-16 | |||
JP2020001059A | 2020-01-09 | |||
JP2017030014A | 2017-02-09 | |||
JP2020123775A | 2020-08-13 |
Other References:
See also references of EP 4173750A4
Attorney, Agent or Firm:
EIKOH PATENT FIRM, P.C. (JP)
Download PDF:
Previous Patent: OPTICAL DEVICE
Next Patent: COMMUNICATION DEVICE, COMMUNICATION SYSTEM, COMMUNICATION CONTROL METHOD, AND PROGRAM
Next Patent: COMMUNICATION DEVICE, COMMUNICATION SYSTEM, COMMUNICATION CONTROL METHOD, AND PROGRAM