Method and apparatus for determining the health of a component using condition indicators
First Claim
1. A method for determining a health indicator associated with a component, comprising:
- determining a plurality of health classifications;
determining at least one condition indicator guantifying a characteristic of said component;
determining a probability associated with each of said health classifications, said probability being an estimation that said component is of a particular health classification given said at least one condition indicator; and
determining, for a given set of observed values, which of said plurality of health classifications is associated with said component using said probabilities associated with said health classifications, wherein said determining at least one condition indicator, said determining a probability, and said determining which of said health classifications is associated with said component, are performed upon two of said plurality of health classifications, and wherein, if a determination is made that a first of said health classifications is not associated with said component, repeating said determining at least one condition indicator, said determining a probability, and said determining which of said health classifications is associated with said component using two other health classifications.
2 Assignments
0 Petitions
Accused Products
Abstract
Disclosed are techniques used in connection with determining a health indicator (HI) of a component, such as that of an aircraft component. The HI is determined using condition indicators (CIs) which parameterize characteristics about a component minimizing possibility of a false alarm. Different algorithms are disclosed which may be used in determining one or more CIs. The HI may be determined using a normalized CI value. Techniques are also described in connection with selecting particular CIs that provide for maximizing separation between HI classifications. Given a particular HI at a point in time for a component, techniques are described for predicting a future state or health of the component using the Kalman filter. Techniques are described for estimating data values as an alternative to performing data acquisitions, as may be used when there is no pre-existing data.
49 Citations
18 Claims
-
1. A method for determining a health indicator associated with a component, comprising:
-
determining a plurality of health classifications;
determining at least one condition indicator guantifying a characteristic of said component;
determining a probability associated with each of said health classifications, said probability being an estimation that said component is of a particular health classification given said at least one condition indicator; and
determining, for a given set of observed values, which of said plurality of health classifications is associated with said component using said probabilities associated with said health classifications, wherein said determining at least one condition indicator, said determining a probability, and said determining which of said health classifications is associated with said component, are performed upon two of said plurality of health classifications, and wherein, if a determination is made that a first of said health classifications is not associated with said component, repeating said determining at least one condition indicator, said determining a probability, and said determining which of said health classifications is associated with said component using two other health classifications. - View Dependent Claims (2, 3)
storing previously observed and calculated data associated with said component; and
using a portion of said previously observed and calculated data to determine said probability associated with said each health classification.
-
-
3. The method of claim 1, further comprising:
-
obtaining data estimates using models of said component; and
using said data estimates to determine said probability associated with said each health classification.
-
-
4. A method for determining a health indicator associated with a component, comprising:
-
determining a plurality of health classifications;
determining at least one condition indicator quantifying a characteristic of said component;
determining a probability associated with each of said health classifications, said probability being an estimation that said component is of a particular health classification given said at least one condition indicator;
determining, for a given set of observed values, which of said plurality of health classifications is associated with said component using said probabilities associated with said health classifications;
determining a threshold using a ratio of a portion of said probabilities;
calculating a current quantity associated with said component using said observed values; and
comparing said current quantity to said ratio to determine which of said health classifications is associated with said component. - View Dependent Claims (5, 6)
determining a transformation matrix maximizing a distance between two of said plurality of health classifications;
determining a covariance matrix for each of said health classifications using said at least one condition indicator and said observed values; and
determining said current quantity in accordance with said covariance matrices, said transformation matrix and said observed values.
-
-
6. The method of claim 5, wherein, for two of said plurality of health classifications, said current quantity, h(X), may be represented as:
-
7. A method for determining a health status of a component comprising:
-
selecting a plurality of condition indicators having a value and each having a corresponding weighting factor, and at least one threshold value defining at least two health classifications;
determining a contribution to a health indicator for each of said condition indicators, wherein said determining further comprises, for each of said plurality of indicators;
determining which of said at least two classifications said value of said each condition indicator belongs; and
determining said contribution to said health indicator by said each condition indicator in accordance with a selected one of said at least two classifications and said weighted factor; and
determining said health indicator according to all contributions by each of said condition indicator values. - View Dependent Claims (8, 9)
determining that said contribution to said health indicator for a first of said condition indicators is zero if said value of said condition indicator is in said first classification;
determining that said contribution to said health indicator is a first multiple of said weighting factor if said value of said condition indicator is in said second classification; and
determining that said contribution to said health indicator is a second multiple of said weighting factor if said value of said condition indicator is in said third classification.
-
-
9. The method of claim 8, where the two threshold values are alarm level and warning level.
-
10. A computer program product executed on a processor for determining a health indicator associated with a component, comprising machine executable code for
determining a plurality of health classifications; -
determining at least one condition indicator quantifying a characteristic of said component;
determining a probability associated with each of said health classifications, said probability being an estimation that said component is of a particular health classification given said at least one condition indicator; and
determining, for a given set of observed values, which of said plurality of health classifications is associated with said component using said probabilities associated with said health classifications, wherein machine executable code for determining at least one condition indicator, determining a probability, and determining which of said health classifications is associated with said component, are performed upon two of said plurality of health classifications, and the computer program product further includes machine executable code, wherein, if a determination is made that a first of said health classifications is not associated with said component, for repeatedly determining at least one condition indicator, repeatedly determining a probability, and repeatedly determining which of said health classifications is associated with said component using two other health classifications. - View Dependent Claims (11, 12)
storing previously observed and calculated data associated with said component; and
using a portion of said previously observed and calculated data to determine said probability associated with each health classification.
-
-
12. The computer program product of claim 10, further comprising machine executable code for:
-
obtaining data estimates using models of said component; and
using said data estimates to determine said probability associated with said each health classification.
-
-
13. A computer program product executed on a processor for determining a health indicator associated with a component, comprising machine executable code for
determining a plurality of health classifications; -
determining at least one condition indicator quantifying a characteristic of said component;
determining a probability associated with each of said health classifications, said probability being an estimation that said component is of a particular health classification given said at least one condition indicator;
determining, for a given set of observed values, which of said plurality of health classifications is associated with said component using said probabilities associated with said health classifications, determining a threshold using a ratio of a portion of said probabilities;
calculating a current quantity associated with said component using said observed values; and
comparing said current quantity to said ratio to determine which of said health classifications is associated with said component. - View Dependent Claims (14, 15)
determining a transformation matrix maximizing a distance between two of said plurality of health classifications;
determining a covariance matrix for each of said health classifications using said at least one condition indicator and said observed values; and
determining said current quantity in accordance with said covariance matrices, said transformation matrix and said observed values.
-
-
15. The computer program product of claim 14, wherein, for two of said plurality of health classifications, said current quantity, h(X), may be represented as:
-
16. A computer program product executed on a processor for determining a health status of a component comprising machine executable code for:
-
selecting a plurality of condition indicators having a value and each having a corresponding weighting factor, and at least one threshold value defining at least two health classifications;
determining a contribution to a health indicator for each of said condition indicators, wherein said machine executable code for determining further comprises, for each of said plurality of indicators, machine executable code for;
determining which of said at least two classifications said value of said each condition indicator belongs; and
determining said contribution to said health indicator by said each condition indicator in accordance with a selected one of said at least two classifications and said weighted factor; and
determining said health indicator according to all contributions by each of said condition indicator values. - View Dependent Claims (17, 18)
determining that said contribution to said health indicator for a first of said condition indicators is zero if said condition indicator is in said first classification;
determining that said contribution to said health indicator is a first multiple of said weighting factor if said condition indicator is in said second classification; and
determining that said contribution to said health indicator is a second multiple of said weighting factor if said condition indicator is in said third classification.
-
-
18. The computer program product of claim 17, where the two threshold values are alarm level and warning level.
Specification