UTILIZATION OF IMAGE ANALYTICS TO DETECT ABNORMALITIES ON FAN BLADES OF GAS TURBINE ENGINES

UTILIZATION OF IMAGE ANALYTICS TO DETECT ABNORMALITIES ON FAN BLADES OF GAS TURBINE ENGINES

Methods of inspecting fan blades (70) of a gas turbine engine (20) for abnormalities are disclosed. One method utilizes a neural network (108) to determine whether a photographic image (114) of at least one fan blade (70) depicts an abnormality of the at least one fan blade (70). Another method uses...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: LINCOLN, David L, HAGEN, Gregory S, GOYETTE, Scott, ATTRIDGE, Paul, LEE, Jeremiah C, LORE, Kin Gwn, CHAUDHRY, Zaffir A
Format: Patent
Sprache:eng ; fre ; ger
Schlagworte:
CALCULATING
COMPUTING
COUNTING
IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
PHYSICS
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Methods of inspecting fan blades (70) of a gas turbine engine (20) for abnormalities are disclosed. One method utilizes a neural network (108) to determine whether a photographic image (114) of at least one fan blade (70) depicts an abnormality of the at least one fan blade (70). Another method uses a dimensional reduction technique on one or more first photographic images (110) that depict at least one first fan blade (70) to obtain basis vectors, utilizes the basis vectors to obtain a reconstructed version of a second photographic image (114) that depicts at least one second fan blade (70), and determines whether the at least one second fan blade (70) includes an abnormality based on a difference between the second photographic image (114) and the reconstructed version of the second photographic image (114). Another method determines whether a fan blade (70) includes an abnormality based on contrast differences between adjacent areas of an image.