EP-4740076-A1 - DEFECT DETECTION IN AIRCRAFT ENGINES USING VISUAL NEUROMORPHIC SENSORS

Abstract

Embodiments of the present disclosure generally relate to aircraft engines and, more particularly, to detecting defects in aircraft engines using visual neuromorphic sensors. In some embodiments, an event associated with a portion of an aircraft engine may be identified based on a change on a visual data characteristic from a visual neuromorphic sensor. In response to identifying the event associated with the portion of the aircraft engine, synchronous data from a synchronous data collection sensor coupled to the aircraft engine may be retrieved for a predetermined period of time, and a defect associated with the aircraft engine detected based on the identified event and the synchronous data. Other embodiments may be disclosed or claimed.

Inventors

• REDDY, Kishore K.
• LORE, Kin Gwn
• SUNDARAMOORTHI, Ganesh

Assignees

• RTX Corporation

Dates

Publication Date

20260513

Application Date

20240708

Claims (20)

1. 1. A data acquisition system for an aircraft engine, the data acquisition system comprising: a visual neuromorphic sensor for monitoring a portion of the aircraft engine; a synchronous data collection sensor; a processor coupled to the visual neuromorphic sensor and the synchronous data collection sensor; and memory coupled to the processor and storing instructions that, when executed by the processor, cause the data acquisition system to: receive first data from the visual neuromorphic sensor, the first data including a visual data characteristic associated with an image of the portion of the aircraft engine; receive second data from the visual neuromorphic sensor subsequent to receiving the first data, wherein the second data indicates a change in the visual data characteristic; identify, based on the change in the visual data characteristic, an event associated with the portion of the aircraft engine; in response to identifying the event associated with the portion of the aircraft engine, retrieve synchronous data from the synchronous data collection sensor for a predetermined period of time; and detect, based on the identified event and the synchronous data, a defect associated with the portion of the aircraft engine.
2. 2. The data acquisition system of claim 1, wherein the change in the visual data characteristic includes one or more of: a change in a pixel of the image, a change in contrast of the image, a change in brightness of the image, and a change in an illumination level of the image.
3. 3. The data acquisition system of claim 1, wherein detecting the defect associated with the portion of the aircraft engine is based on providing information associated with the event and the synchronous data to a neural network to determine a probability associated with the defect.
4. 4. The data acquisition system of claim 1, wherein the synchronous data collection sensor includes one or more of: a gyroscope, an accelerometer, a motion sensor, and a speed sensor.
5. 5. The data acquisition system of claim 1, wherein the portion of the aircraft engine includes a fan blade.
6. 6. The data acquisition system of claim 1, wherein the portion of the aircraft engine includes a circuit board.
7. 7. The data acquisition system of claim 1 , wherein the visual neuromorphic sensor includes an electro-optical/infra-red (EO/IR) camera.
8. 8. A computer-readable medium storing instructions that, when executed by a data acquisition system, cause the data acquisition system to: receive first data from a visual neuromorphic sensor for monitoring a portion of the aircraft engine, the first data including a visual data characteristic associated with an image of the portion of the aircraft engine; receive second data from the visual neuromorphic sensor subsequent to receiving the first data, wherein the second data indicates a change in the visual data characteristic; identify, based on the change in the visual data characteristic, an event associated with the portion of the aircraft engine; in response to identifying the event associated with the portion of the aircraft engine, retrieve synchronous data from a synchronous data collection sensor for a predetermined period of time; and detect, based on the identified event and the synchronous data, a defect associated with the portion of the aircraft engine.
9. 9. The computer-readable medium of claim 8, wherein the change in the visual data characteristic includes one or more of: a change in a pixel of the image, a change in contrast of the image, a change in brightness of the image, and a change in an illumination level of the image.
10. 10. The computer-readable medium of claim 8, wherein detecting the defect associated with the portion of the aircraft engine is based on providing information associated with the event and the synchronous data to a neural network to determine a probability associated with the defect.
11. 1 1. The computer-readable medium of claim 8, wherein the synchronous data collection sensor includes one or more of: a gyroscope, an accelerometer, a motion sensor, and a speed sensor.
12. 12. The computer-readable medium of claim 8, wherein the portion of the aircraft engine includes a fan blade.
13. 13. The computer-readable medium of claim 8, wherein the portion of the aircraft engine includes a circuit board.
14. 14. The computer-readable medium of claim 8, wherein the visual neuromorphic sensor includes an electro-optical/infra-red (EO/IR) camera.
15. 15. A computer-implemented method, comprising: receiving, by a data acquisition system, first data from a visual neuromorphic sensor for monitoring a portion of the aircraft engine, the first data including a visual data characteristic associated with an image of the portion of the aircraft engine; receiving, by the data acquisition system, second data from the visual neuromorphic sensor subsequent to receiving the first data, wherein the second data indicates a change in the visual data characteristic; identifying, by the data acquisition system and based on the change in the visual data characteristic, an event associated with the portion of the aircraft engine; in response to identifying the event associated with the portion of the aircraft engine, retrieving, by the data acquisition system, synchronous data from a synchronous data collection sensor for a predetermined period of time; and detecting, by the data acquisition system and based on the identified event and the synchronous data, a defect associated with the portion of the aircraft engine.
16. 16. The computer- implemented method of claim 15, wherein the change in the visual data characteristic includes one or more of: a change in a pixel of the image, a change in contrast of the image, a change in brightness of the image, and a change in an illumination level of the image.
17. 17. The computer-implemented method of claim 15, wherein detecting the defect associated with the portion of the aircraft engine is based on providing information associated with the event and the synchronous data to a neural network to determine a probability associated with the defect.
18. 18. The computer-implemented method of claim 15, wherein the synchronous data collection sensor includes one or more of: a gyroscope, an accelerometer, a motion sensor, and a speed sensor.
19. 19. The computer-implemented method of claim 15, wherein the portion of the aircraft engine includes one or more of: a fan blade, and a circuit board.
20. 20. The computer-implemented method of claim 15, wherein the visual neuromorphic sensor includes an electro-optical/infra-red (EO/IR) camera.

Description

DEFECT DETECTION IN AIRCRAFT ENGINES USING VISUAL NEUROMORPHIC SENSORS CROSS-REFERENCE TO RELATED APPLICATIONS [0001] This application claims the benefit of U.S. Provisional Application No. 63/512,462 filed July 7, 2023, the disclosure of which is incorporated herein by reference in its entirety. TECHNICAL FIELD [0002] The subject matter disclosed herein generally relates to aircraft engines and, more particularly, to detecting defects in aircraft engines using visual neuromorphic sensors. BACKGROUND [0003] Engines, such as gas turbine engines, hydroelectric turbine engines, and/or the like, can be used to provide thrust to aircraft and/or other types of vehicles. In some cases, such engines can include one or more sensors to monitor the status of the engine and detect anomalies occurring within the engine. For example, a temperature sensor can sense temperature within the engine (or within a section of the engine) and can indicate when an anomaly has occurred, such as the measured temperature exceeding a temperature threshold. [0004] Neuromorphic sensors are sensors that detect changes in data characteristics monitored by the neuromorphic sensor. For example, a visual neuromorphic sensor (also referred to as an “event camera”) may detect local changes to an image of a monitored object, such as a change in a pixel of the image, a change in brightness in the image, and/or a change in illumination level. In contrast to sensors that synchronously report a data characteristic at predetermined intervals (regardless of whether the data characteristic changes), a neuromorphic sensor asynchronously reports only the changes to the data characteristic. BRIEF DESCRIPTION [0005] In one exemplary embodiment, a data acquisition system for an aircraft engine is provided. The data acquisition system includes a visual neuromorphic sensor for monitoring a portion of the aircraft engine, a synchronous data collection sensor, a processor coupled to the visual neuromorphic sensor and the synchronous data collection sensor, and memory coupled to the processor. The memory stores instructions that, when executed by the processor, cause the data acquisition system to receive first data from the visual neuromorphic sensor, the first data including a visual data characteristic associated with an image of the portion of the aircraft engine. The memory further stores instructions to cause the data acquisition system to receive second data from the visual neuromorphic sensor subsequent to receiving the first data, wherein the second data indicates a change in the visual data characteristic. The memory further stores instructions to cause the data acquisition system to identify, based on the change in the visual data characteristic, an event associated with the portion of the aircraft engine. The memory further stores instructions to cause the data acquisition system to, in response to identifying the event associated with the portion of the aircraft engine, retrieve synchronous data from the synchronous data collection sensor for a predetermined period of time. The memory further stores instructions to cause the data acquisition system to detect, based on the identified event and the synchronous data, a defect associated with the portion of the aircraft engine. [0006] In addition to one or more of the features described herein, or as an alternative, further embodiments of the data acquisition system may include that the change in the visual data characteristic includes one or more of: a change in a pixel of the image, a change in contrast of the image, a change in brightness of the image, and a change in an illumination level of the image. [0007] In addition to one or more of the features described herein, or as an alternative, further embodiments of the data acquisition system may include that detecting the defect associated with the portion of the aircraft engine is based on providing information associated with the event and the synchronous data to a neural network to determine a probability associated with the defect. [0008] In addition to one or more of the features described herein, or as an alternative, further embodiments of the data acquisition system may include that the synchronous data collection sensor includes one or more of: a gyroscope, an accelerometer, a motion sensor, and a speed sensor. [0009] In addition to one or more of the features described herein, or as an alternative, further embodiments of the data acquisition system may include that the portion of the aircraft engine includes a fan blade and/or a circuit board. [0010] In addition to one or more of the features described herein, or as an alternative, further embodiments of the data acquisition system may include that the visual neuromorphic sensor includes an electro-optical/infra-red (EO/IR) camera. [0011] In another exemplary embodiment, a computer-readable medium is provided. The computer-readable medium stores instructions that, when executed by a da