US-12617549-B2 - Aircraft engine anomaly detection based on odor, sound, and/or image

US12617549B2US 12617549 B2US12617549 B2US 12617549B2US-12617549-B2

Abstract

Examples described herein provide a method for aircraft engine anomaly detection based on an odor. The method includes receiving data indicative of the odor associated with an aircraft engine of an aircraft. The method further includes analyzing the data to determine whether an anomaly associated with the aircraft has occurred. The method further includes responsive to determining that an anomaly associated with the aircraft has occurred, implementing a corrective action based at least in part on the data.

Inventors

Stephen A. Witalis
Ramesh Rajagopalan

Assignees

RTX CORPORATION

Dates

Publication Date: 20260505
Application Date: 20230802

Claims (15)

1 . A method for aircraft engine anomaly detection based on an odor, the method comprising: receiving from at least one odor detection sensor data indicative of the odor associated with an aircraft engine of an aircraft, the at least one odor detection sensor configured to sample an airflow through the aircraft engine according to a schedule; analyzing the data to determine whether an anomaly associated with the aircraft has occurred; responsive to determining that an anomaly associated with the aircraft has occurred, implementing a corrective action based at least in part on the data; and updating the schedule based on the data.
2 . The method of claim 1 , wherein the data indicative of the odor is received from a plurality of odor detection sensors.
3 . The method of claim 1 , wherein the data is current data, wherein analyzing the data comprises comparing the current data to historical data, and wherein an anomaly associated with the aircraft is determined to have occurred responsive to a change between the historical data and the current data.
4 . The method of claim 1 , wherein analyzing the data comprises comparing the data to a threshold, and wherein an anomaly associated with the aircraft is determined to have occurred responsive to the data exceeding the threshold.
5 . The method of claim 1 , wherein analyzing the data comprises classifying the odor using a machine learning model.
6 . The method of claim 5 , further comprising training the machine learning model.
7 . The method of claim 1 , wherein the aircraft engine is selected from a group consisting of a gas turbine engine, an electric engine, and a hybrid electric turbine engine.
8 . A full authority digital engine control comprising: a memory comprising computer readable instructions; and a processing device for executing the computer readable instructions, the computer readable instructions controlling the processing device to perform operations for aircraft engine anomaly detection based on a sound, the operations comprising: receiving from at least one sound detection sensor sound data indicative of the sound associated with an aircraft engine of an aircraft, at least one sound detection sensor configured to sample the aircraft engine according to a sound detection schedule; receiving odor from at least one odor detection sensor data indicative of the odor associated with an aircraft engine of an aircraft, the at least one odor detection sensor configured to sample an airflow through the aircraft engine according to an odor detection schedule; analyzing the sound data and the odor data to determine whether an anomaly associated with the aircraft has occurred; responsive to determining that an anomaly associated with the aircraft has occurred, implementing a corrective action based at least in part on the sound data; and updating the odor detection schedule based on the odor data, and the sound detection schedule based on the sound data.
9 . The full authority digital engine control of claim 8 , wherein the odor data indicative of the odor is received from a plurality of odor detection sensors, and wherein the sound data indicative of the sound is received from a plurality of sound detection sensors.
10 . The full authority digital engine control of claim 8 , wherein analyzing the sound data comprises applying a machine learning model to infer a type of the anomaly.
11 . The full authority digital engine control of claim 8 , wherein the odor data is current odor data, wherein analyzing the odor data comprises comparing the current odor data to historical odor data, wherein an anomaly associated with the aircraft is determined to have occurred responsive to a change between the historical odor data and the current odor data, wherein the sound data is current sound data, wherein analyzing the sound data comprises comparing the current sound data to historical sound data, and wherein an anomaly associated with the aircraft is determined to have occurred responsive to a change between the historical sound data and the current sound data.
12 . The full authority digital engine control of claim 8 , wherein analyzing the odor data comprises comparing the odor data to an odor threshold, wherein analyzing the sound data comprises comparing the sound data to a sound threshold and a known signature sound profile, and wherein an anomaly associated with the aircraft is determined to have occurred responsive to the odor data exceeding the odor threshold and the sound data exceeding the sound threshold.
13 . A non-transitory computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to perform operations comprising: receiving from at least one odor detection sensor odor data indicative of an odor associated with an aircraft engine of an aircraft and receiving sound data indicative of a sound associated with the aircraft engine, the at least one odor detection sensor configured to sample an airflow through the aircraft engine according to a schedule; analyzing the odor data or the sound data to determine whether an anomaly associated with the aircraft has occurred; responsive to determining that an anomaly associated with the aircraft has occurred, receiving image data from an image sensor associated with aircraft; analyzing the image data to verify the anomaly; responsive to verifying the anomaly, implementing a corrective action based at least in part on the odor data or the sound data; and updating the schedule based on the odor data.
14 . The non-transitory computer program product of claim 13 , wherein the anomaly is an electrical fire, and wherein the corrective action is to activate a fire suppression system.
15 . The non-transitory computer program product of claim 14 , wherein the anomaly is volcanic ash being ingested into the aircraft engine, and wherein the corrective action is to open a bleed air port of the aircraft engine.

Description

CROSS REFERENCE TO RELATED APPLICATIONS This application claims priority to U.S. Provisional Application No. 63/395,154 filed Aug. 4, 2022, the entire contents of which are incorporated herein by reference thereto. TECHNICAL FIELD The subject matter disclosed herein generally relates to aircraft engines and particularly to aircraft engine anomaly detection. BACKGROUND 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 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. BRIEF DESCRIPTION In one exemplary embodiment, a method aircraft engine anomaly detection based on an odor is provided. The method includes receiving data indicative of the odor associated with an aircraft engine of an aircraft. The method further includes analyzing the data to determine whether an anomaly associated with the aircraft has occurred. The method further includes responsive to determining that an anomaly associated with the aircraft has occurred, implementing a corrective action based at least in part on the data. In addition to one or more of the features described herein, or as an alternative, further embodiments of the method may include that the data indicative of the odor is received from an odor detection sensor. In addition to one or more of the features described herein, or as an alternative, further embodiments of the method may include that the data indicative of the odor is received from a plurality of odor detection sensors. In addition to one or more of the features described herein, or as an alternative, further embodiments of the method may include that the plurality of odor detection sensors sample an airflow through the aircraft engine according to a schedule. In addition to one or more of the features described herein, or as an alternative, further embodiments of the method may include updating the scheduled based on the data. In addition to one or more of the features described herein, or as an alternative, further embodiments of the method may include that the data is current data, wherein analyzing the data comprises comparing the current data to historical data, and wherein an anomaly associated with the aircraft is determined to have occurred responsive to a change between the historical data and the current data. In addition to one or more of the features described herein, or as an alternative, further embodiments of the method may include that analyzing the data comprises comparing the data to a threshold, and wherein an anomaly associated with the aircraft is determined to have occurred responsive to the data satisfying the threshold. In addition to one or more of the features described herein, or as an alternative, further embodiments of the method may include that analyzing the data comprises classifying the odor using a machine learning model. In addition to one or more of the features described herein, or as an alternative, further embodiments of the method may include training the machine learning model. In addition to one or more of the features described herein, or as an alternative, further embodiments of the method may include that the aircraft engine is selected from a group consisting of a gas turbine engine, an electric engine, and a hybrid electric turbine engine. In another exemplary embodiment a full authority digital control includes a memory including computer readable instructions and a processing device for executing the computer readable instructions. The computer readable instructions control the processing device to perform operations for aircraft engine anomaly detection based on a sound. The operations include receiving sound data indicative of the sound associated with an aircraft engine of an aircraft. The operations further include receiving odor data indicative of the odor associated with an aircraft engine of an aircraft. The operations further include analyzing the sound data and the odor data to determine whether an anomaly associated with the aircraft has occurred. The operations further include, responsive to determining that an anomaly associated with the aircraft has occurred, implementing a corrective action based at least in part on the sound data. In addition to one or more of the features described herein, or as an alternative, further embodiments of the full authority digital engine control may include that the odor data indicative of the odor is received from an odor detection sensor, and wherein the sound data indicative of the sound is received from a sound detection sensor. In addition to one or more of the features described herein, or as an alternative, further embodiments of