IP Library › Granted Patent US 12,639,803
Granted Patent B2
US 12,639,803 · App. 18/348,495 · Granted May 26, 2026

Systems and methods for material accretion detection and removal

Inventors: John Karigiannis (Laval, CA); Arpit Jain (Fremont, CA); Raju D. Venkataramana (Camas, WA); Jose Antonio Cuevas Alvarez (Turgi, CH); David Michael Boehmer (Atlanta, GA); Sam Van Orman (Atlanta, GA)
Assignee: GE Infrastructure Technology LLC
G06T7/001F01D25/02F05D2270/8041
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 12,639,803
App. No.
18/348,495
Granted
May 26, 2026
Kind
B2
Abstract

A system for monitoring at least one component is provided. The system includes at least one processor in communication with at least one memory device. The at least one processor is programmed to store a plurality of baseline information associated with the at least one component to be monitored and receive a plurality of current images of the at least one component to be monitored. The at least one processor is also programmed to detect a deviation from baseline based upon a comparison of the plurality of current images and the plurality of baseline information. The at least one processor is further programmed to classify the deviation and implement a corrective action based on the classification of deviation.

Claims (50)

1 . A system for monitoring at least one component using at least one processor in communication with at least one memory device, wherein the at least one processor is programmed to:

store a plurality of baseline information associated with the at least one component to be monitored;

receive a plurality of current images of the at least one component to be monitored;

detect a deviation from baseline based upon a comparison of the plurality of current images and the plurality of baseline information;

receive contextual sensor information from one or more sensors measuring internal operational parameters of the component to be monitored, wherein the internal operational parameters are separate from the deviation;

execute a machine-learning trained model to classify the deviation, wherein the machine-learning trained model is trained to classify deviations and identify a material of the deviation based upon the plurality of baseline information, the contextual sensor information received, and a plurality of historical images of the at least one component to be monitored; and

implement a corrective action based on the classification of deviation.

2 . The system of claim 1 , wherein the at least one processor is further programmed to:

determine an amount of deviation based on the comparison; and

determine which of a plurality of corrective actions should be implemented.

3 . The system of claim 1 , wherein the at least one processor is further programmed to:

notify a user via a client device that a corrective action should be activated;

receive a response from the user; and

activate the corrective action based upon the user response.

4 . The system of claim 1 , wherein the at least one processor is further programmed to activate at least one mitigation system when:

the detected deviation is determined to be ice accumulation; and

the determined amount of accumulation exceeds a predetermined threshold.

5 . The system of claim 4 , wherein the at least one processor is further programmed to:

monitor an amount of deviation detected during activation of the at least one mitigation system; and

deactivate the at least one mitigation system when a detected amount of deviation no longer exceeds a predetermined threshold.

6 . The system of claim 1 , wherein the at least one processor is further programmed to receive environmental sensor information from one or more sensors monitoring an environment of the at least one component including at least one of temperature and humidity of the environment of the at least one component.

7 . The system of claim 6 , wherein the at least one processor is further programmed to determine whether the deviation may occur based on environmental conditions based on the environmental sensor information received including at least one of temperature and humidity.

8 . The system of claim 1 , wherein the at least one processor is further programmed to classify the deviation by a cause of the deviation, wherein the cause of the deviation includes at least one of damage to one or more parts of the machine, a calibration need for one or more parts of the machine, missing components or portions of components of the machine, and leakage present.

9 . The system of claim 1 , wherein the deviation is an accretion of material and wherein the material includes at least one of dirt, dust, and oil.

10 . The system of claim 1 , wherein the at least one component is a part of a turbine and wherein the plurality of current images are transmitted from a camera viewing a compressor through a window defined in an inlet plenum.

11 . A method for monitoring at least one component within a device, the method implemented on a computer system including at least one processor in communication with at least one memory device, the method comprising:

storing a plurality of baseline information associated with the at least one component to be monitored;

receiving a plurality of current images of the at least one component to be monitored;

detecting a deviation from baseline based upon the plurality of current images and the plurality of baseline information;

receiving contextual sensor information from one or more sensors measuring internal operational parameters of the component to be monitored, wherein the internal operational parameters are separate from the deviation;

executing a machine-learning trained model to classify the deviation, wherein the machine-learning trained model is trained to classify deviations and identify a material of the deviation based upon the plurality of baseline information, the contextual sensor information received, and a plurality of historical images of the at least one component to be monitored; and

implementing a corrective action based on the classification of deviation.

12 . The method of claim 11 further comprising:

determining an amount of deviation based on the comparison; and

determining which of a plurality of corrective actions should be implemented.

13 . The method of claim 11 further comprising:

notify a user via a client device that a corrective action should be activated;

receiving a response from the user; and

activating the corrective based upon the response.

14 . The method of claim 11 further comprising activate at least one mitigation system when:

the detected deviation is determined to be ice accumulation; and

the determined amount of accumulation exceeds a predetermined threshold.

15 . The method of claim 14 further comprising:

monitoring an amount of deviation detected during activation of the at least one mitigation system; and

deactivating the at least one mitigation system when a detected amount of deviation no longer exceeds a predetermined threshold.

16 . The method of claim 11 further comprising receiving environmental sensor information from one or more sensors monitoring an environment of the device including at least one of temperature and humidity of the environment of the device.

17 . The method of claim 16 further comprising determining whether the deviation may occur based on environmental conditions based on the environmental sensor information received including at least one of temperature and humidity.

18 . The method of claim 11 , wherein the device is a turbine and wherein the plurality of current images are transmitted from a camera viewing a compressor through a window defined in an inlet plenum.

19 . The method of claim 11 further comprising classifying the deviation by a cause of the deviation, wherein the cause of the deviation includes at least one of damage to one or more parts of the machine, a calibration need for one or more parts of the machine, missing components or portions of components of the machine, and leakage present.

20 . The method of claim 11 , wherein the deviation is an accretion of material and wherein the material includes at least one of dirt, dust, and oil.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 7, 2023
From: KARIGIANNIS, JOHN; JAIN, ARPIT; VENKATARAMANA, RAJU D.; CUEVAS ALVAREZ, JOSE ANTONIO; BOEHMER, DAVID MICHAEL; VAN ORMAN, SAM
To: GE INFRASTRUCTURE TECHNOLOGY LLC
Reel/Frame 064182/0422 →
Continuity (1)
Related Publication 20250014168A1 · Jan 9, 2025
References Cited (25)
US 7439877B1 · Jarvinen · 2008 [cited by examiner]
US 9097657B2 · Xu · 2015 [cited by applicant]
US 9170193B2 · Xu et al. · 2015 [cited by applicant]
US 9567907B2 · Bhabhrawala · 2017 [cited by applicant]
US 9759630B2 · Xu et al. · 2017 [cited by applicant]
US 9874109B2 · Clifford, Jr. et al. · 2018 [cited by applicant]
US 10495545B2 · Moore et al. · 2019 [cited by applicant]
US 10508597B2 · Kalya et al. · 2019 [cited by applicant]
US 11145202B1 · Buentello · 2021 [cited by examiner]
US 12147944B2 · Malkan · 2024 [cited by examiner]
US 20150047368A1 · Jones et al. · 2015 [cited by applicant]
US 20170090458A1 · Lim et al. · 2017 [cited by applicant]
US 20180321386A1 · Bosetti · 2018 [cited by examiner]
US 20180336674A1 · Lim · 2018 [cited by examiner]
US 20190146000A1 · Hurst et al. · 2019 [cited by applicant]
US 20190225346A1 · Calmels · 2019 [cited by examiner]
US 20210071897A1 · Casa · 2021 [cited by examiner]
US 20210372375A1 · Schaper · 2021 [cited by examiner]
US 20230152792A1 · Mears · 2023 [cited by examiner]
US 20230219698A1 · Campbell · 2023 [cited by examiner]
US 20250390845A1 · Upadhya · 2025 [cited by examiner]
EP 3214519B1 · 2020 [cited by applicant]
Myshkin, Nikolai K., and Liubou V. Markova. “Wear prediction for tribosystems based on debris analysis.” On-Line Condition Monitoring in Industrial Lubrication and Tribology. Cham: Springer International Publishing, 201… [cited by examiner]
Laninga, J., Nasr Esfahani, A., Ediriweera, G., Jacob, N. and Kordi, B., 2023. Monitoring technologies for HVDC transmission lines. Energies, 16(13), p. 5085. (Year: 2023). [cited by examiner]
European Search Report received for 24181920 on Nov. 13, 2024; 9 pps. [cited by applicant]