Granted Patent B2

US 12,559,256 · App. 18/519,418 · Granted Feb 24, 2026

Inventors: Jean-Marie Dautelle (Blagnac, FR); Sara Wallinger (Hamburg, DE)

Assignees: Airbus SAS; Airbus Operations GmbH

B64F5/40B64F5/60

Abstract

Claims (45)

1 . A method for determining a probability of occurrence of a malfunction creating a performance defect in an aircraft, the method being executed by a computing system comprising electronic circuitry that implements the following steps:

acquiring a set of input data each relating to the occurrence of the malfunction in the aircraft, each input datum comprising a timestamped notification of the malfunction and a timestamped record of measurements from sensors of the aircraft;

grouping the input data into groups of malfunctions having the same root cause;

delimiting a causal time window for the malfunction, an upper bound of the causal time window being the timestamped notification of the malfunction, and, for each input datum, retaining only a sample containing measurements contained within the causal time window;

weighting each measurement of the same sample, a sum of weights of the same sample being equal to 1;

filtering the measurements of each sample so as to retain only measurements of interest with respect to the malfunction;

comparing the measurements of interest of each sample with reference measurements, and for each measurement of interest of a sample that is greater than the corresponding reference measurement, assigning a first Boolean value to the measurement of interest, and for each measurement of interest of a sample that is less than the corresponding reference measurement, assigning a second Boolean value to the measurement of interest different from the first Boolean value, so as to obtain a series of Boolean values;

splitting each group into a plurality of subgroups, each subgroup corresponding to a variation of one or more Boolean values of the series of Boolean values, such that, for each group, there are 2n subgroups, where n is a number of Boolean values, and dividing each sample of the same group into a subgroup corresponding to the Boolean values of each sample;

calculating a sum of the weights of the measurements of each subgroup;

using the sum of the weights of each subgroup to determine a probability of occurrence of the malfunction for each subgroup; and

carrying out a maintenance action on an aircraft according to the determined probability of occurrence of the malfunction.

2 . The method according to claim 1 , wherein the weight of each measurement is calculated according to W=1/N, where: W is the weight and N is a number of measurements in the sample.

3 . The method according to claim 1 , wherein the weight of each measurement is corrected according to

W

⁢

c

=

C

⁢

W

⁡

(

-

t

)

×

W

N

⁢

F

,

where Wc is the corrected weight, CW is a causal time window and NF is a normalization factor.

4 . The method according to claim 3 , wherein the normalization factor NF is calculated according to: NF=Σ CW(−t)×W.

5 . The method according to claim 1 , wherein a learning system uses the sum of the weights of each subgroup to determine a probability of occurrence of the malfunction for each subgroup.

6 . A non-transient storage medium on which there is stored a computer program comprising program code instructions for executing the method according to claim 1 when said instructions are read from said non-transient storage medium and executed by a processor.

7 . A computing system comprising electronic circuitry configured to determine a probability of occurrence of a malfunction creating a performance defect in an aircraft, the electronic circuitry implementing at least the following steps:

acquiring a set of input data each relating to the occurrence of said malfunction in the aircraft, each input datum comprising a timestamped notification of the malfunction and a timestamped record of measurements from sensors of the aircraft;

grouping the input data into groups of malfunctions having the same root cause;

delimiting a causal time window for the malfunction, an upper bound of the causal time window being the timestamped notification of the malfunction, and, for each input datum, retaining only a sample containing measurements contained within the causal time window;

weighting each measurement of the same sample, a sum of weights of the same sample being equal to 1;

filtering the measurements of each sample so as to retain only measurements of interest with respect to the malfunction;

comparing the measurements of interest of each sample with reference measurements, and for each measurement of interest of a sample that is greater than the corresponding reference measurement, assigning a first Boolean value to said measurement of interest, and for each measurement of interest of a sample that is less than the corresponding reference measurement, assigning a second Boolean value to said measurement of interest different from the first Boolean value, so as to obtain a series of Boolean values;

splitting each group into a plurality of subgroups, each subgroup corresponding to a variation of one or more Boolean values of the series of Boolean values, such that, for each group, there are 2n subgroups, where n is a number of Boolean values, and dividing each sample of the same group into a subgroup corresponding to the Boolean values of each sample;

calculating the sum of the weights of the measurements of each subgroup; and

using the sum of the weights of each subgroup to determine a probability of occurrence of the malfunction for each subgroup.

Assignments (1)

Priority Claims (1)

Continuity (1)

References Cited (17)