ENGINE MONITORING

• US 20110191002A1
• Filed: 01/20/2011
• Published: 08/04/2011
• Est. Priority Date: 02/01/2010
• Status: Active Grant

• Current Assignee: Rolls-Royce PLC (Rolls-Royce Holdings Plc)
• Original Assignee: Rolls-Royce PLC (Rolls-Royce Holdings Plc)
• Inventors: GOPSILL, James A., WHATLEY, Paul D.
• Granted Patent: US 9,104,199 B2
• Time in Patent Office: Days
• US Class Current: 701/99
• CPC Class Codes: F02D 41/22 Safety or indicating devices for abnormal conditions in air/fuel ratio feedback systems F02D41/1495, in electric control linkage F02D11/107, in purge control systems F02M25/0809
• CPC Class Codes: F02D 41/2496 the memory being part of a closed loop
• CPC Class Codes: F02D 41/26 using computer, e.g. microprocessor
• CPC Class Codes: G05B 23/024 Quantitative history assessment, e.g. mathematical relationships between available data; Functions therefor; Principal component analysis [PCA]; Partial least square [PLS]; Statistical classifiers, e.g. Bayesian networks, linear regression or correlation analysis; Neural networks

Abstract

A method of monitoring a device, the method comprising: measuring one or more device operating parameters and a device performance parameter during one or more device operational periods; recording a plurality of data points, each data point comprising the device operating parameters and the associated device performance parameter; identifying one or more steady state regions in the device performance parameter and selecting a plurality of the data points from the one or more steady state regions in the device performance parameter; selecting one or more groups (40) of the steady state data points in the device operating parameter space by virtue of a predetermined density of the steady state data points in the device operating parameter space; and comparing the device performance parameter within the groups so as to identify a change in the performance of the device.

Claims

1. A method of monitoring a device, the method comprising:

measuring one or more device operating parameters and a device performance parameter during one or more device operational periods;

recording a plurality of data points, each data point comprising the device operating parameters and the associated device performance parameter;

identifying one or more steady state regions in the device performance parameter and selecting a plurality of the data points from the one or more steady state regions in the device performance parameter;

selecting one or more groups of the steady state data points in the device operating parameter space by virtue of a predetermined density of the steady state data points in the device operating parameter space; and

comparing the device performance parameter within the groups so as to identify a change in the performance of the device.

2. A method of monitoring a device as claimed in claim 1, wherein the method further comprises:

calculating differences between successive device performance parameter values; and

identifying regions in which the absolute value of the differences are below a threshold value in order to identify the one or more steady state regions in the device performance parameter.

3. A method of monitoring a device as claimed in claim 1, wherein the method further comprises:

calculating a first ratio of the change in the device performance parameter over a time period with respect to a datum steady state data point and a first successive device performance parameter;

calculating a second ratio of the change in the device performance parameter to a time period with respect to the datum steady state data point and a second successive device performance parameter;

calculating differences between the first and second ratios for a range of datum steady state data points; and

identifying regions in which the absolute value of the differences are below a threshold value in order to identify the one or more steady state regions in the device performance parameter.

4. A method of monitoring a device as claimed in claim 3, wherein the method further comprises:

calculating changes in the differences between first and second ratios for successive datum data points; and

identifying regions in which the absolute value of the changes are below a threshold value in order to identify the one or more steady state regions in the device performance parameter.

5. A method of monitoring a device as claimed in claim 1, wherein the method further comprises:

counting the number of steady state data points neighbouring a particular steady state data point within a predetermined domain about the particular steady state data point in the device operating parameter space;

repeating for each steady state data point; and

grouping steady state data points with a number of neighbouring steady state data points above a predetermined threshold into the one or more groups.

6. A method of monitoring a device as claimed in claim 5, wherein the predetermined domain about the particular steady state data point in the device operating parameter space is determined by a predetermined range for each of the one or more operating parameters in the device operating parameter space.

7. A method of monitoring a device as claimed in claim 6, wherein the predetermined range is the same for two or more of the operating parameters.

8. A method of monitoring a device as claimed in claim 6, wherein the predetermined range for a particular device operating parameter varies according to the value of the device operating parameter.

9. A method of monitoring a device as claimed in claim 5, wherein all points defining a boundary of the predetermined domain in the device operating parameter space are equidistant from the particular steady state data point.

10. A method of monitoring a device as claimed in claim 5, wherein the method further comprises:

calculating the distances between a steady state data point within the one or more groups and each of the remaining steady state data points within the one or more groups in the device operating parameter space; and

identifying the steady state data points within a group by virtue of their proximity to one another so as to distinguish between the one or more groups.

11. A method of monitoring a device as claimed in claim 1, wherein the method further comprises:

adjusting a device control parameter in response to the change in the performance of the device.

12. A method of monitoring a device as claimed in claim 1, wherein the method further comprises:

performing maintenance on the device in response to the change in the performance of the device.

13. A method of monitoring a device as claimed in claim 1, wherein the method further comprises:

monitoring a further device; and

comparing the device performance parameter within the groups and between devices so as to identify a change in the performance of either device.

14. A method of monitoring a device as claimed in claim 1, wherein the device performance parameter comprises one or more of a power output, a shaft speed, flow rates, fluid temperatures, fluid pressures, lubricant temperatures, lubricant pressures, device component temperatures, vibration levels, noise levels, strain levels and any other indicator of device performance.

15. A method of monitoring a device as claimed in claim 1, wherein the one or more device operating parameters comprises one or more of ambient pressure, ambient temperature, ambient humidity, power input, power demand, fuel consumption rate, fuel calorific value, altitude, speed and any other indicator of device operating conditions.

16. A method of monitoring a device as claimed in claim 1, wherein the method is applied to a plurality of device performance parameters.

17. A method of monitoring a device as claimed in claim 1, wherein the device comprises an engine.

18. A computer program, which when executed on a computer, causes it to carry out a method of monitoring a device, the method comprising:

measuring one or more device operating parameters and a device performance parameter during one or more device operational periods;

recording a plurality of data points, each data point comprising the device operating parameters and the associated device performance parameter;

identifying one or more steady state regions in the device performance parameter and selecting a plurality of the data points from the one or more steady state regions in the device performance parameter;

selecting one or more groups of the steady state data points in the device operating parameter space by virtue of a predetermined density of the steady state data points in the device operating parameter space; and

comparing the device performance parameter within the groups so as to identify a change in the performance of the device.

19. A computer storage medium comprising a computer program according to claim 18.

20. Apparatus for monitoring a device, the apparatus comprising a processor operable to:

receive one or more device operating parameters and a device performance parameter during one or more device operational periods;

record a plurality of data points, each data point comprising the device operating parameters and the associated device performance parameter;

identify one or more steady state regions in the device performance parameter and select a plurality of the data points from the one or more steady state regions in the device performance parameter;

select one or more groups of the steady state data points in the device operating parameter space by virtue of a predetermined density of the steady state data points in the device operating parameter space; and

compare the device performance parameter within the groups so as to identify a change in the performance of the device.