IP Library › Granted Patent US 12,571,740
Granted Patent B2
US 12,571,740 · App. 18/105,299 · Granted Mar 10, 2026

Utilization of image analytics to detect abnormalities on fan blades of gas turbine engines

Inventors: Jeremiah C. Lee (Coventry, CT); Paul Attridge (Colchester, CT); Zaffir A. Chaudhry (South Glastonbury, CT); Scott Goyette (Moosup, CT); Gregory S. Hagen (Glastonbury, CT); David L. Lincoln (Cromwell, CT); Kin Gwn Lore (Belmont, MA)
Assignee: RTX Corporation
G01N21/9515G01N21/8851G06F18/2135G06T7/0004G01N2021/1765G01N2021/8861G01N2021/8887G06T2207/20081G06T2207/20084
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,571,740
App. No.
18/105,299
Filed
Feb 3, 2023
Granted
Mar 10, 2026
Kind
B2
Examiner
LAU, TUNG S
Art Unit
2857
USPC
702/81
Abstract

Methods of inspecting fan blades of a gas turbine engine for abnormalities are disclosed. One method utilizes a neural network to determine whether a photographic image of at least one fan blade depicts an abnormality of the at least one fan blade. Another method uses a dimensional reduction technique on one or more first photographic images that depict at least one first fan blade to obtain basis vectors, utilizes the basis vectors to obtain a reconstructed version of a second photographic image that depicts at least one second fan blade, and determines whether the at least one second fan blade includes an abnormality based on a difference between the second photographic image and the reconstructed version of the second photographic image. Another method determines whether a fan blade includes an abnormality based on contrast differences between adjacent areas of an image.

Claims (21)

1 . A method of inspecting fan blades of a gas turbine engine for abnormalities, comprising:

obtaining, by one or more processors of a computing device, a set of one or more first photographic images that depict at least one first fan blade of one or more first gas turbine engines, the set of one or more first photographic images having initial dimensions corresponding to attributes of pixels of the one or more first photographic images, and the computing device comprising at least the one or more processors, a memory element, and a communication interface;

utilizing, by the one or more processors, a dimensional reduction technique on the set of one or more first photographic images to obtain a set of basis vectors for representing the set of first photographic images in a reduced dimensional space that is reduced with respect to the initial dimensions, wherein the dimensional reduction technique is Principal Component Analysis (PCA);

obtaining, by the one or more processors from at least one camera, a second photographic image that is not part of the set and that depicts at least one second fan blade of a second gas turbine engine, the at least one camera being situated within a nacelle of the second gas turbine engine, and the one or more processors being communicatively coupled to the at least one camera via a communication interface of the computing device;

utilizing the set of basis vectors to obtain a reconstructed version of the second photographic image that reconstructs the second photographic image in the reduced dimensional space;

based on a difference between the second photographic image and the reconstructed version of the second photographic image exceeding a predefined difference threshold, determining, by the one or more processors, that the at least one second fan blade of the second gas turbine includes an abnormality and

providing a blade abnormality notification, by the one or more processors, the blade abnormality notification comprising at least one of: logging the abnormality in the memory element, providing a visible notification, and providing an audible notification.

2 . The method of claim 1 , comprising, prior to said utilizing a dimensional reduction technique to obtain the set of basis vectors:

dividing at least one of the one or more first photographic images in the set into a plurality of patches that represent areas of the one of more first images;

wherein said utilizing the dimensional reduction technique on the set of one or more first photographic images comprises utilizing the dimensional reduction technique on the plurality of patches; and

wherein the basis vectors correspond to features common to all of the patches from the one or more first photographic images.

3 . The method of claim 1 , comprising:

modifying portions of at least one of the one or more first photographic images by using one or more of the following techniques: scaling, cropping, rotating, gamma correction, and contrast adjustment; and

wherein said utilizing a dimensional reduction technique on the set of one or more first images is performed on an augmented set of the first photographic images that includes the modified portions.

4 . The method of claim 1 , comprising:

modifying portions of at least one of the one or more first photographic images by adding blurring to said portions; and

wherein said utilizing a dimensional reduction technique on the set of one or more first images is performed on an augmented set of the first photographic images that includes the modified portions.

5 . The method of claim 1 , comprising:

modifying portions of at least one of the one or more first photographic images by modifying a brightness of said portions to simulate lighting conditions that differ from those of said at least one of the one or more first photographic images; and

wherein said utilizing a dimensional reduction technique on the set of one or more first images is performed on an augmented set of the first photographic images that includes the modified portions.

6 . The method of claim 1 , wherein none of said one or more first photographic images includes the abnormality.

Assignments (2)
CHANGE OF NAME Recorded Jul 27, 2023
From: RAYTHEON TECHNOLOGIES CORPORATION
To: RTX CORPORATION
Reel/Frame 064402/0837 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 27, 2023
From: LEE, JEREMIAH C.; ATTRIDGE, PAUL; CHAUDHRY, ZAFFIR A.; GOYETTE, SCOTT; HAGEN, GREGORY S.; LINCOLN, DAVID L.; LORE, KIN GWN
To: RAYTHEON TECHNOLOGIES CORPORATION
Reel/Frame 063105/0842 →
Continuity (1)
Related Publication 20240264092A1 · Aug 8, 2024
References Cited (15)
US 8528317B2 · Gerez et al. · 2013 [cited by applicant]
US 9476798B2 · Pandey · 2016 [cited by applicant]
US 10504220B2 · Lim et al. · 2019 [cited by applicant]
US 10691985B2 · Lim et al. · 2020 [cited by applicant]
US 10914191B2 · Finn et al. · 2021 [cited by applicant]
US 20060023961A1 · Suh · 2006 [cited by examiner]
US 20090066939A1 · Venkatachalam et al. · 2009 [cited by applicant]
US 20090097729A1 · Venkatachalam et al. · 2009 [cited by applicant]
US 20120078097A1 · Wang · 2012 [cited by examiner]
US 20190338666A1 · Finn et al. · 2019 [cited by applicant]
US 20220215522A1 · Vorobieva et al. · 2022 [cited by applicant]
CN 110792563A · 2020 [cited by examiner]
CN 111178392 · 2020 [cited by applicant]
European Search Report for European Patent Application No. 24155616.6 dated Oct. 30, 2024. [cited by applicant]
Aust et al., “Automated defect detection and decision-support in gad turbine blade inspection”, Aerospace, vol. 8, No. 2, p. 30, Jan. 26, 2021. [cited by applicant]