MACHINE LEARNING SYSTEM FOR IN-SITU RECOGNITION OF COMMON LOCATIONS IN A ROTATABLE BODY WITH REPEATING SEGMENTS
Patent №
US 10,691,985
Granted
2020-06-23
Filed 2017
Owner
GENERAL ELECTRIC COMPANY
Lab
—
AI components
1
vision
Assignment
Recorded
Dataset
AIPD
2023_r1 edition
Application
15714208
A system includes one or more processors configured to automatically identify different distressed portions in repeating segments of a rotating body. At least one of a size and/or a shape of one or more of the distressed portions changes with respect to time. The one or more processors also are configured to determine a pattern of the different distressed portions in the repeating segments of the rotating body during rotation of the rotating body based on identifying the different distressed portions. The one or more processors also are configured to subsequently automatically identify locations of individual segments of the repeating segments in the rotating body using the pattern of the distressed portions that is determined.
AI classification
Ownership
GENERAL ELECTRIC COMPANY
assignment · 436820147
Assignors
LIM, SER NAM, DIWINSKY, DAVID SCOTT
On an employer assignment, the assignors are typically the inventors.