US 12,422,331 B2
Methods and apparatus to autonomously detect thermal anomalies
Brandon S. Good, Niskayuna, NY (US); Bijan Chitsaz, Evendale, OH (US); Guanghua Wang, Niskayuna, NY (US); Bernard P. Bewlay, Niskayuna, NY (US); Gyeong Woo Cheon, Niskayuna, NY (US); and Alberto Santamaria-Pang, Bellevue, WA (US)
Assigned to General Electric Company, Evandale, OH (US)
Filed by General Electric Company, Schenectady, NY (US)
Filed on Apr. 25, 2024, as Appl. No. 18/646,462.
Application 18/646,462 is a continuation of application No. 17/538,717, filed on Nov. 30, 2021, granted, now 11,971,329.
Prior Publication US 2024/0369441 A1, Nov. 7, 2024
Int. Cl. G01M 3/38 (2006.01); F02C 7/00 (2006.01); G01J 5/00 (2022.01); G06T 7/00 (2017.01); G06T 7/90 (2017.01); G08B 21/18 (2006.01); H04N 23/90 (2023.01)
CPC G01M 3/38 (2013.01) [F02C 7/00 (2013.01); G01J 5/0003 (2013.01); G06T 7/0002 (2013.01); G06T 7/90 (2017.01); G08B 21/182 (2013.01); H04N 23/90 (2023.01); F05D 2260/80 (2013.01); G01J 2005/0077 (2013.01); G06T 2207/10048 (2013.01); G06T 2207/20084 (2013.01)] 17 Claims
OG exemplary drawing
 
1. An apparatus to detect engine anomalies comprising:
at least one memory to store instructions; and
processor circuitry to execute the instructions to:
determine a difference between a baseline image set and a reconstructed image set based on:
a ratio of the baseline image set to the reconstructed image set; and
a neighboring area estimation to identify an engine anomaly;
generate an alert indicating detection of the engine anomaly based on the difference between the baseline image set and the reconstructed image set; and
generate a reconstructed image set using an artificial intelligence model to compare the reconstructed image set to the baseline image set.