# US 2023/0167836 A1 · Prognostication and amelioration of gas ingress in hydraulic systems

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

- Number: US 2023/0167836 A1
- Document ID: US20230167836A1
- Status: Published application
- Kind: A1
- Application number: 17/539,887
- Filed: 2021-12-01
- Published: 2023-06-01
- Earliest claimed: 2021-12-01
- Assignees: The Boeing Company
- Applicants: The Boeing Company
- Inventors: Jun Yuan
- Web page: https://patentgrep.com/patent/US20230167836A1

## CPC

- B64D 45/00: Aircraft indicators or protectors not otherwise provided for
- F15B 21/044: Removal or measurement of undissolved gas, e.g. de-aeration, venting or bleeding
- B64D 43/00: Arrangements or adaptations of instruments
- G06F 17/12: Simultaneous equations {, e.g. systems of linear equations}
- B64D 2045/0085: {Devices for aircraft health monitoring, e.g. monitoring flutter or vibration}
- F15B 2201/205: using gas
- F15B 2201/505: Testing of accumulators, e.g. for testing tightness
- F15B 2211/857: Monitoring of fluid pressure systems
- B64D: EQUIPMENT FOR FITTING IN OR TO AIRCRAFT; FLIGHT SUITS; PARACHUTES; ARRANGEMENT OR MOUNTING OF POWER PLANTS OR PROPULSION TRANSMISSIONS IN AIRCRAFT
- F15B: SYSTEMS ACTING BY MEANS OF FLUIDS IN GENERAL; FLUID-PRESSURE ACTUATORS, e.g. SERVOMOTORS; DETAILS OF FLUID-PRESSURE SYSTEMS, NOT OTHERWISE PROVIDED FOR
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

Prognostication and amelioration of gas ingress in hydraulic systems can be provided by identifying a stable reading window when operating a carrying system comprising a hydraulic system; collecting a set of fluid level readings of a hydraulic fluid in the hydraulic system during a plurality of stable reading windows across a corresponding plurality of operational instances of the carrying system; calculating median fluid levels in each stable reading window of the plurality of stable reading windows; identifying an increasing trend in the median fluid levels when analyzed as time series data that satisfies a trend threshold of at least a predefined number successive indications of increased fluid levels in the hydraulic fluid within an analysis window; and generating an alert of gas ingress to the hydraulic system.

## Claims

### Claim 1

A method, comprising:
identifying a stable reading window when operating a carrying system comprising a hydraulic system;
collecting a set of fluid level readings of a hydraulic fluid in the hydraulic system during a plurality of stable reading windows across a corresponding plurality of operational instances of the carrying system;
calculating median fluid levels in each stable reading window of the plurality of stable reading windows;
identifying an increasing trend in the median fluid levels when analyzed as time series data that satisfies a trend threshold of at least a predefined number successive indications of increased fluid levels in the hydraulic fluid within an analysis window; and
generating an alert of gas ingress to the hydraulic system.

### Claim 2 (depends on 1)

The method of claim 1, further comprising:
calculating standard deviations in the set of fluid level readings for each stable reading window of the plurality of stable reading windows;
fitting a regression model to the median fluid levels as the time series data;
calculating a mean square error for the standard deviations; and
excluding a given instance of the median fluid levels when analyzing the time series data when the mean square error associated with the given instance is above an outlier threshold.

### Claim 3 (depends on 1)

The method of claim 1, wherein:
the carrying system is an aircraft;
the stable reading window occurs a first threshold number of minutes before a middle of cruise time and the first threshold number of minutes after the middle of cruise time; and
the middle of cruise time occurs at least a second threshold number of minutes after reaching a top of climb and at least the second threshold number of minutes before reaching a top of descent during a given operational instance of the carrying system.

### Claim 4 (depends on 1)

The method of claim 1, further comprising:
identifying a given operational instance of the plurality of operational instances in which sensors in the carrying system unrelated to the hydraulic system indicate an operational aberration;
excluding a given instance of the median fluid levels associated with the given operational instance when analyzing the time series data; and
bifurcating the time series data to represent operational instances before the operational aberration and operational instances after the operational aberration.

### Claim 5 (depends on 1)

The method of claim 1, wherein analyzing the median fluid levels as the time series data further comprises:
identifying a set of successive operational instances from the plurality of operational instances;
clustering, via an unsupervised machine learning technique, the set of successive operational instances into a first cluster and a second cluster based on associated median fluid levels associated with the set of successive operational instances and associated operational times associated with the set of successive operational instances;
determining a distance between a first centroid value for the first cluster and a second centroid value for the second cluster based on the associated median fluid levels; and
excluding a latest operational instance of the set of successive operation instances from analysis in response to at least one of:
a first sum of squared distances, between the first centroid value and each member of the first cluster exceeding, a sum squared error threshold;
a second sum of squared distances, between the second centroid value and each member of the second cluster, exceeding the sum squared error threshold; and
the distance between the first centroid value and the second centroid value exceeds a service specification indicative of the hydraulic fluid being serviced within the set of successive operation instances.

### Claim 6 (depends on 1)

The method of claim 1, wherein generating the alert of gas ingress to the hydraulic system further comprises:
identifying that the increasing trend holds true for a majority of the predefined number successive indications of the increased fluid levels in the hydraulic fluid.

### Claim 7 (depends on 1)

The method of claim 1, wherein generating the alert of gas ingress to the hydraulic system further comprises:
identifying that the increased fluid levels in the hydraulic fluid comprise at least a threshold amount over a nominal fill level for the hydraulic fluid.

### Claim 8

A system, comprising:
a processor; and
a memory, including instructions that when executed by the processor perform operations comprising:
identifying a stable reading window when operating a carrying system comprising a hydraulic system;
collecting a set of fluid level readings of a hydraulic fluid in the hydraulic system during a plurality of stable reading windows across a corresponding plurality of operational instances of the carrying system;
calculating median fluid levels in each stable reading window of the plurality of stable reading windows;
identifying an increasing trend in the median fluid levels when analyzed as time series data that satisfies a trend threshold of at least a predefined number successive indications of increased fluid levels in the hydraulic fluid within an analysis window; and
generating an alert of gas ingress to the hydraulic system.

### Claim 9 (depends on 8)

The system of claim 8, wherein the operations further comprise:
calculating standard deviations in the set of fluid level readings for each stable reading window of the plurality of stable reading windows;
fitting a regression model to the median fluid levels as the time series data;
calculating a mean square error for the standard deviations; and
excluding a given instance of the median fluid levels when analyzing the time series data when the mean square error associated with the given instance is above an outlier threshold.

### Claim 10 (depends on 8)

The system of claim 8, wherein:
the carrying system is an aircraft;
the stable reading window occurs a first threshold number of minutes before a middle of cruise time and the first threshold number of minutes after the middle of cruise time; and
the middle of cruise time occurs at least a second threshold number of minutes after reaching a top of climb and at least the second threshold number of minutes before reaching a top of descent during a given operational instance of the carrying system.

### Claim 11 (depends on 8)

The system of claim 8, wherein the operations further comprise:
identifying a given operational instance of the plurality of operational instances in which sensors in the carrying system unrelated to the hydraulic system indicate an operational aberration;
excluding a given instance of the median fluid levels associated with the given operational instance when analyzing the time series data; and
bifurcating the time series data to represent operational instances before the operational aberration and operational instances after the operational aberration.

### Claim 12 (depends on 8)

The system of claim 8, wherein analyzing the median fluid levels as the time series data further comprises:
identifying a set of successive operational instances from the plurality of operational instances;
clustering, via an unsupervised machine learning technique, the set of successive operational instances into a first cluster and a second cluster based on associated median fluid levels associated with the set of successive operational instances and associated operational times associated with the set of successive operational instances;
determining a distance between a first centroid value for the first cluster and a second centroid value for the second cluster based on the associated median fluid levels; and
excluding a latest operational instance of the set of successive operation instances from analysis in response to at least one of:
a first sum of squared distances, between the first centroid value and each member of the first cluster exceeding, a sum squared error threshold;
a second sum of squared distances, between the second centroid value and each member of the second cluster, exceeding the sum squared error threshold; and
the distance between the first centroid value and the second centroid value exceeds a service specification indicative of the hydraulic fluid being serviced within the set of successive operation instances.

### Claim 13 (depends on 8)

The system of claim 8, wherein generating the alert of gas ingress to the hydraulic system further comprises:
identifying that the increasing trend holds true for a majority of the predefined number successive indications of the increased fluid levels in the hydraulic fluid.

### Claim 14 (depends on 8)

The system of claim 8, wherein generating the alert of gas ingress to the hydraulic system further comprises:
identifying that the increased fluid levels in the hydraulic fluid comprise at least a threshold amount over a nominal fill level for the hydraulic fluid.

### Claim 15

A memory device including instructions that when executed by a processor perform operations comprising:
identifying a stable reading window when operating a carrying system comprising a hydraulic system;
collecting a set of fluid level readings of a hydraulic fluid in the hydraulic system during a plurality of stable reading windows across a corresponding plurality of operational instances of the carrying system;
calculating median fluid levels in each stable reading window of the plurality of stable reading windows;
identifying an increasing trend in the median fluid levels when analyzed as time series data that satisfies a trend threshold of at least a predefined number successive indications of increased fluid levels in the hydraulic fluid within an analysis window; and
generating an alert of gas ingress to the hydraulic system.

### Claim 16 (depends on 15)

The memory device of claim 15, wherein the operations further comprise:
calculating standard deviations in the set of fluid level readings for each stable reading window of the plurality of stable reading windows;
fitting a regression model to the median fluid levels as the time series data;
calculating a mean square error for the standard deviations; and
excluding a given instance of the median fluid levels when analyzing the time series data when the mean square error associated with the given instance is above an outlier threshold.

### Claim 17 (depends on 15)

The memory device of claim 15, wherein:
the carrying system is an aircraft;
the stable reading window occurs a first threshold number of minutes before a middle of cruise time and the first threshold number of minutes after the middle of cruise time; and
the middle of cruise time occurs at least a second threshold number of minutes after reaching a top of climb and at least the second threshold number of minutes before reaching a top of descent during a given operational instance of the carrying system.

### Claim 18 (depends on 15)

The memory device of claim 15, further comprising:
identifying a given operational instance of the plurality of operational instances in which sensors in the carrying system unrelated to the hydraulic system indicate an operational aberration;
excluding a given instance of the median fluid levels associated with the given operational instance when analyzing the time series data; and
bifurcating the time series data to represent operational instances before the operational aberration and operational instances after the operational aberration.

### Claim 19 (depends on 15)

The memory device of claim 15, wherein generating the alert of gas ingress to the hydraulic system further comprises:
identifying that the increasing trend holds true for a majority of the predefined number successive indications of the increased fluid levels in the hydraulic fluid.

### Claim 20 (depends on 15)

The memory device of claim 15, wherein generating the alert of gas ingress to the hydraulic system further comprises:
identifying that the increased fluid levels in the hydraulic fluid comprise at least a threshold amount over a nominal fill level for the hydraulic fluid.
