Patent · US Active

System and methods for labeling weld monitoring time periods using machine learning techniques

US11400537B2 · kind B2 · utility

1Cited by
54References
20Claims
0Family size

Assignee

Inventor

Key dates

Filing dateAug 3, 2020
Grant dateAug 2, 2022
Priority date
Expiry dateSep 1, 2040

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N20/00
  • WIPO fieldMachine tools
  • WIPO sectorMechanical engineering

Abstract

Systems and methods for labeling non-welding time periods using machine learning techniques are described. In some examples, a weld monitoring system may collect various data from sensors and/or welding equipment in a welding area over a time period. The data may evaluated to divide the time period into welding time periods and non-welding time periods. The weld monitoring system may use one or more machine learning models and/or techniques in combination with the collected data to determine what non-welding activities took place during the non-welding time periods. In some examples, the machine learning models may be continuously trained, updated, and/or improved using feedback from operators and/or other individuals, data from ongoing welding and/or non-welding activities, as well as data from other weld monitoring systems and/or machine learning models.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.