# US 10,767,507 B2 · Foreign object debris trending concept and design

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 10,767,507 B2
- Document ID: US10767507B2
- Status: Granted
- Kind: B2
- Application number: 15/350,886
- Filed: 2016-11-14
- Published: 2018-05-17
- Granted: 2020-09-08
- Earliest claimed: 2016-11-14
- Assignees: Raytheon Technologies Corporation
- Applicants: United Technologies Corporation
- Inventors: Alexander I Khibnik; Gregory S Hagen
- Web page: https://patentgrep.com/patent/US10767507B2

## CPC

- F01D 21/003: {Arrangements for testing or measuring (for measuring vibrations G01H)}
- F02C 7/05: having provisions for obviating the penetration of damaging objects or particles
- G01M 15/14: Testing gas-turbine engines or jet-propulsion engines
- F05D 2220/32: in gas turbines
- F05D 2260/607: Preventing clogging or obstruction of flow paths by dirt, dust, or foreign particles
- F05D 2260/80: Diagnostics
- F05D 2260/81: Modelling or simulation
- F05D 2260/83: Testing, e.g. methods, components or tools therefor
- G05B 23/0221: {Preprocessing measurements, e.g. data collection rate adjustment; Standardization of measurements; Time series or signal analysis, e.g. frequency analysis or wavelets; Trustworthiness of measurements; Indexes therefor; Measurements using easily measured parameters to estimate parameters difficult to measure; Virtual sensor creation; De-noising; Sensor fusion; Unconventional preprocessing inherently present in specific fault detection methods like PCA-based methods}
- Y02T 50/60: Efficient propulsion technologies, e.g. for aircraft
- F01D: NON-POSITIVE DISPLACEMENT MACHINES OR ENGINES, e.g. STEAM TURBINES (machines or engines for liquids F03; non-positive displacement pumps F04D)
- F02C: GAS-TURBINE PLANTS; AIR INTAKES FOR JET-PROPULSION PLANTS; CONTROLLING FUEL SUPPLY IN AIR-BREATHING JET-PROPULSION PLANTS (construction of turbines F01D; jet-propulsion plants F02K; construction of compressors or fans F04; generating combustion products of high pressure or high velocity F23R; using gas turbines in compression refrigeration plants F25B11/00)
- G01M: TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- F05D: INDEXING SCHEME FOR ASPECTS RELATING TO NON-POSITIVE-DISPLACEMENT MACHINES OR ENGINES, GAS-TURBINES OR JET-PROPULSION PLANTS
- G05B: CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS (systems for controlling or regulating non-electric variables G05D; systems for regulating electric or magnetic variables G05F; control devices or systems insofar as characterised by mechanical features only G05G)
- Y02T: CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION

## Abstract

A system and method for detecting foreign object debris damage is disclosed. A method for foreign object debris detection in a gas turbine engine may include receiving, by a controller, a first time-series data from a database, wherein the first time-series data comprises a feature, pre-processing, by the controller, the first time-series data to generate a second time-series data, generating a third time-series data via an anomaly detector model, sending, by the controller, the third time-series data to a foreign object debris (FOD) damage model, and determining, by the controller, that a FOD event has occurred based on data received from the FOD damage model. In various embodiments, the method may further comprise generating, by the controller, a health report (HR).

## Claims

### Claim 1

A method for foreign object debris (FOD) detection in a gas turbine engine comprising:
receiving, by a controller, a first feature data from a database, wherein the first feature data comprises a first feature, the first feature data measured by a first gas turbine engine sensor;
receiving, by the controller, a second feature data from the database, wherein the second feature data comprises a second feature, wherein the first feature is different from the second feature, and the second feature data is measured by the first gas turbine engine sensor;
pre-processing, by the controller, the first feature data, wherein the pre-processing further causes the controller to calculate a derived parameter using the first feature data;
generating a first anomaly detection signal, via an anomaly detector model, using the first feature data and the derived parameter, wherein the first anomaly detection signal indicates at least one anomaly based upon the first feature;
generating a second anomaly detection signal, via the anomaly detector model, using the second feature data, wherein the second anomaly detection signal indicates at least one other anomaly based upon the second feature;
sending, by the controller, the first anomaly detection signal to a FOD damage model;
sending, by the controller, the second anomaly detection signal to the FOD damage model;
determining, by the controller, that a FOD event has occurred based upon the first anomaly detection signal and the second anomaly detection signal; and
generating, by the controller, a health report (HR) indicating the likelihood that the FOD event has occurred based upon the first anomaly detection signal and the second anomaly detection signal.

### Claim 2 (depends on 1)

The method of claim 1, wherein the pre-processing further causes the controller to at least one of:
evaluate an integrity of the first feature data;
evaluate a health of the first gas turbine engine sensor; or
clean the first feature data.

### Claim 3 (depends on 1)

The method of claim 1, wherein the generating the first anomaly detection signal includes calculating, by the controller, an anomaly detector, wherein the anomaly detector is based upon the first feature data.

### Claim 4 (depends on 3)

The method of claim 3, wherein the calculating the anomaly detector includes analyzing the first feature data, the first anomaly detection signal comprising a vector of values including the anomaly detector.

### Claim 5 (depends on 4)

The method of claim 4, wherein the first anomaly detection signal comprises at least one of a Boolean value or a characteristic value providing information about an anomaly.

### Claim 6 (depends on 4)

The method of claim 4, wherein the anomaly detector model is configured to produce the first anomaly detection signal comprising the anomaly detector in response to receiving the first feature data.

### Claim 7 (depends on 6)

The method of claim 6, wherein at least one of the first feature data, the second feature data, the first anomaly detection signal, the second anomaly detection signal, the anomaly detector, the HR, the anomaly detector model, or the FOD damage model are stored in the database, wherein the database is in electronic communication with the controller.

### Claim 8 (depends on 1)

The method of claim 1, wherein the pre-processing further causes the controller to at least one of:
align the first feature data with respect to time;
define a filter for the first feature data; and
define a point of interest of the first feature data.

### Claim 9

A system for foreign object debris (FOD) detection in a gas turbine engine, comprising:
a controller in electronic communication with a memory, the controller configured to:
receive a first time-series data from the memory, wherein the first time-series data is measured by a first debris monitoring sensor coupled to the gas turbine engine;
receive a second time-series data from the memory, wherein the second time-series data is measured by a second debris monitoring sensor coupled to the gas turbine engine, wherein the first debris monitoring sensor monitors a compressor section of the gas turbine engine and the second debris monitoring sensor monitors a turbine section of the gas turbine engine, the compressor section drives air along a core flow-path for compression and communication into a combustor section and subsequently expansion through the turbine section;
generate a first feature data based upon a first calculation using the first time-series data;
generate a second feature data based upon a second calculation selectively using at least one of the first time-series data or the second time-series data, wherein the first calculation is different from the second calculation in response to the second calculation being performed using the first time-series data;
detect at least one anomaly in the first feature data;
detect at least one other anomaly in the second feature data;
determine an occurrence of a FOD event based upon the at least one anomaly and the least one other anomaly, wherein the at least one anomaly corresponds to a first FOD event in the compressor section of the gas turbine engine and the at least one other anomaly corresponds to a second FOD event in the turbine section of the gas turbine engine; and
report a FOD damage health report (HR) in response to the calculated anomaly indicating the occurrence of a FOD event.

### Claim 10 (depends on 9)

The system of claim 9, wherein the controller is further configured to:
evaluate a health of at least one of the first debris monitoring sensor and the second debris monitoring sensor;
clean the first time-series data;
align the first time-series data with respect to time;
define a filter for the first time-series data; or
define a point of interest of the first time-series data.

### Claim 11 (depends on 9)

The system of claim 9, wherein the controller generates an anomaly detector in response to the controller detecting the at least one anomaly, wherein detecting the at least one anomaly includes analyzing the first time-series data and generating a time-series vector of values including the anomaly detector.

### Claim 12 (depends on 11)

The system of claim 11, wherein the time-series vector comprises a Boolean value.

### Claim 13 (depends on 11)

The system of claim 11, wherein the controller implements an anomaly detector model, the anomaly detector model configured to produce an anomaly detection signal comprising the time series vector of values including the anomaly detector in response to receiving the first time-series data, and wherein the controller implements a FOD damage model, the FOD damage model configured to produce a FOD damage estimate in response to receiving the anomaly detection signal.

### Claim 14 (depends on 13)

The system of claim 13, wherein at least one of the first time-series data, the anomaly detection signal, the anomaly detector, the FOD damage HR, the anomaly detector model, or the FOD damage model are stored in a database, wherein the database is in electronic communication with the controller.

### Claim 15 (depends on 9)

The system of claim 9, wherein the system for foreign object debris detection further comprises a third debris monitoring sensor proximate at least one of a fan section, the compressor section, the combustor section or the turbine section of the gas turbine engine.

### Claim 16 (depends on 9)

The system of claim 9, wherein the first debris monitoring sensor measures the first time-series data at a first sampling rate and the second debris monitoring sensor measures the second time-series data at a second sampling rate, the first sampling rate is different from the second sampling rate.

### Claim 17 (depends on 9)

The system of claim 9, wherein the first debris monitoring sensor is located upstream of the second debris monitoring sensor and the first FOD event in the compressor section is detected at a first time and the second FOD event in the turbine section is detected at a second time, wherein a difference between the first time and the second time corresponds to a time for a foreign object to travel from the first debris monitoring sensor to the second debris monitoring sensor.

### Claim 18

An article of manufacture including a tangible, non-transitory computer-readable storage medium having instructions stored thereon for detecting foreign object debris in a gas turbine engine that, in response to execution by a controller, cause the controller to perform operations comprising:
receiving, by the controller, a first time-series data from the memory, wherein the first time-series data is measured by a first debris monitoring sensor signal;
receiving, by the controller, a second time-series data from the memory, wherein the second time-series data is measured by a second debris monitoring sensor coupled to the gas turbine engine, wherein the first debris monitoring sensor monitors a compressor section of the gas turbine engine and the second debris monitoring sensor monitors a turbine section of the gas turbine engine, the compressor section drives air along a core flow-path for compression and communication into a combustor section and subsequently expansion through the turbine section;
generating, by the controller, a first feature data based upon a first calculation using the first time-series data;
generating, by the controller, a second feature data based upon a second calculation selectively using at least one of the first time-series data or the second time-series data, wherein the first calculation is different from the second calculation in response to the second calculation being performed using the first time-series data;
detecting, by the controller, at least one anomaly in the first feature data;
detecting, by the controller, at least one other anomaly in the second feature data;
determining, by the controller, an occurrence of a FOD event based upon the at least one anomaly and the at least one other anomaly, wherein the at least one anomaly corresponds to a first FOD event in the compressor section of the gas turbine engine and the at least one other anomaly corresponds to a second FOD event in the turbine section of the gas turbine engine; and
reporting, by the controller, a FOD damage health report (HR) in response to the detected anomaly indicating the occurrence of a FOD event.

### Claim 19 (depends on 18)

The article of manufacture of claim 18, wherein the operations further comprise evaluating, by the controller, a health of at least one of the first debris monitoring sensor and the second debris monitoring sensor.

### Claim 20 (depends on 18)

The article of manufacture of claim 18, wherein the operations further comprise at least one of:
cleaning, by the controller, the first time-series data;
aligning, by the controller, the first time-series data with respect to time;
defining, by the controller, a filter for the first time-series data; or
defining, by the controller, a point of interest of the first time-series data.