SYSTEM ABNORMALITIES

• US 20150168264A1
• Filed: 11/26/2014
• Published: 06/18/2015
• Est. Priority Date: 12/13/2013
• Status: Abandoned Application

• Current Assignee: Rolls-Royce Controls and Data Services Limited
• Original Assignee: Rolls-Royce Controls and Data Services Limited
• Inventors: PROCTOR, Samuel Neville
• Application Number:
  US14/554,465
• Publication Number:
  US 20150168264A1
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: F02C 7/00 Features, components parts, details or accessories, not provided for in, or of interest apart form groups F02C1/00 - F02C6/00; Air intakes for jet-propulsion plants controlling F02C9/00
• CPC Class Codes: F05D 2260/80 Diagnostics
• CPC Class Codes: G01M 15/14 Testing gas-turbine engines or jet-propulsion engines
• CPC Class Codes: G05B 23/0235 based on a comparison with predetermined threshold or range, e.g. "classical methods", carried out during normal operation; threshold adaptation or choice; when or how to compare with the threshold
• CPC Class Codes: G05B 23/0283 Predictive maintenance, e.g. involving the monitoring of a system and, based on the monitoring results, taking decisions on the maintenance schedule of the monitored system; Estimating remaining useful life [RUL] preventive maintenance, i.e. planning maintenance according to the available resources without monitoring the system G06Q10/06
• CPC Class Codes: G06F 17/18 for evaluating statistical data , e.g. average values, frequency distributions, probability functions, regression analysis forecasting specially adapted for a specific administrative, business or logistic context G06Q10/04
• CPC Class Codes: G06F 18/24155 Bayesian classification
• CPC Class Codes: G06F 18/2433 Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection

Abstract

A monitor and method to identify an abnormality in a system, including a sensor to measure a parameter value of the system. A processor to receive parameter values; select a subset to store in a buffer; and calculate a threshold corresponding to normal values of the parameter. An estimator to estimate the next parameter value. A comparator to compare a measured parameter value to the calculated threshold and to store: the measured parameter value in the buffer if the measured parameter value does not exceed the calculated threshold and the estimated parameter value in the buffer if the measured parameter value exceeds the calculated threshold.

Claims

1. A monitor to identify an abnormality in a system, the monitor comprising:

a) a sensor to measure a parameter value of the system;

b) a buffer store;

c) a processor to receive parameter values from the sensor;

select a subset of the parameter values to store in the buffer store; and

calculate a threshold corresponding to normal values of the parameter;

d) an estimator to estimate the next parameter value of the system;

e) a comparator to compare a measured parameter value to the calculated threshold and to store the measured parameter value in the buffer store if the measured parameter value does not exceed the calculated threshold and to store the estimated parameter value in the buffer store if the measured parameter value exceeds the calculated threshold; and

f) a recorder to record a parameter abnormality if the measured parameter value exceeds the calculated threshold.

2. A monitor as claimed in claim 1 wherein the processor calculates the threshold by applying Bayesian extreme value theory to the parameter values stored in the buffer store.

3. A monitor as claimed in claim 1 wherein the estimator estimates the next parameter value by applying a Kalman filter to a system state at the previous parameter value.

4. A method to identify an abnormality in a system, the method comprising iterating steps to:

a) periodically measure a parameter of the system to form a data series of parameter values;

b) select a subset of the parameter values from the data series to store in a buffer of parameter values;

c) calculate a threshold corresponding to normal values of the parameter;

d) measure the next value of the parameter;

e) compare the measured parameter value to the calculated threshold and

i) if the measured parameter value does not exceed the calculated threshold, store the measured parameter value in the buffer for subsequent iterations;

or

ii) if the measured parameter value exceeds the calculated threshold, record as a parameter abnormality, estimate the next parameter value in the data series, and store the estimated parameter value in the buffer for subsequent iterations.

5. A method as claimed in claim 4 wherein step 4.b) comprises selecting consecutive parameter values from the data series.

6. A method as claimed in claim 4 wherein step 4.c) comprises applying Bayesian extreme value theory to the parameter values in the buffer.

7. A method as claimed in claim 4 wherein step 4.e)ii) comprises applying a Kalman filter to a system state at the previous parameter value.

8. A method as claimed in claim 4 comprising a further step to report the parameter abnormality.

9. A method as claimed in claim 4 comprising a further step to report an abnormality of the system after three parameter abnormalities have been recorded at step 4.e)ii).

10. A method as claimed in claim 7 wherein the Kalman filter comprises applying a constant multiplier to the system state;

applying a multiplier to the system state that is a function of at least one previous system state;

or comprises a noise component to accommodate random fluctuation in the parameter values.

11. A method as claimed in claim 4 wherein the parameter is measured at predetermined time intervals to form a time series of parameter values.

12. A method as claimed in claim 4 wherein the system comprises an engine or a gas turbine engine.

13. A method as claimed in claim 12 wherein the parameter comprises one of the group comprising a component temperature;

air temperature;

oil temperature;

a pressure;

a shaft speed;

vibration;

clearance between components.

14. A method as claimed in claim 12 wherein the abnormality of the system comprises one or more of the group comprising overspeed of a rotating part of the engine;

underspeed of a rotating part of the engine;

system overheat;

inadequate power output;

failure of a rotating part of the engine.

15. A method as claimed in claim 4 wherein the system comprises a weather system and wherein the parameter comprises one of the group comprising air temperature;

rainfall;

wind speed;

pressure;

air flow.

16. A method as claimed in any of claim 4 wherein step 4.a) comprises periodically measuring more than one parameter of the system and the steps of the method are performed for each parameter;

and the method further comprising a step to report an abnormality of the system if a parameter abnormality is recorded for each parameter at step 4.e)ii).

17. A method as claimed in claim 4 further comprising a step to modify the system in response to a recorded parameter abnormality or in response to a reported abnormality in the system;

and wherein the step of modifying the system comprises one or more of the group comprising;

inspecting a component of the system;

testing a component of the system;

cleaning a component of the system;

performing maintenance actions on a component of the system;

repairing a component of the system;

replacing a component of the system;

inspecting the system;

testing the system;

cleaning the system;

performing maintenance actions on the system;

repairing the system;

removing the system from service.

18. A system health monitor configured to perform the steps of the method according to claim 4.

19. A computer readable medium, having a computer program recorded thereon, wherein the computer program is adapted to make the computer execute the method according to claim 4.

20. A computer program comprising the computer readable medium as claimed in claim 19.