Information processor system for monitoring a complex system

• US 10,393,624 B2
• Filed: 05/22/2013
• Issued: 08/27/2019
• Est. Priority Date: 05/28/2012
• Status: Active Grant

• Current Assignee: Safran Aircraft Engine Company
• Original Assignee: Safran Aircraft Engine Company
• Inventors: Le Gonidec, Serge, Malikov, Dimitri, Berechet, Ion, Berechet, Stefan
• Primary Examiner(s): Dalbo, Michael J
• Application Number:
  US14/400,374
• Publication Number:
  US 20150142366A1
• Time in Patent Office: 2,288 Days
• CPC Class Codes: G01M 15/00 Testing of engines
• CPC Class Codes: G05B 23/0218 characterised by the fault detection method dealing with either existing or incipient faults
• CPC Class Codes: G05B 23/0262 Confirmation of fault detection, e.g. extra checks to confirm that a failure has indeed occurred
• CPC Class Codes: G05B 23/0275 Fault isolation and identification, e.g. classify fault; estimate cause or root of failure
• CPC Class Codes: G05B 23/0278 Qualitative, e.g. if-then rules; Fuzzy logic; Lookup tables; Symptomatic search; FMEA

Abstract

An information processor system for monitoring a complex system and including a mechanism receiving at least one piece of event detection information associated with a detection time and a mechanism generating at least one remanent confidence level value that decreases over time starting from the detection time.

Claims

1. An sensor system for monitoring a complex system comprising:

at least one sensor placed in a particular location in the complex system and configured to detect one or more physical magnitudes whenever a variation is detected relative to a threshold;

processing circuitry configured to

receive at least one piece of event detection information from the at least one sensor associated with a detection time, a fault flag being associated with the at least one piece of event detection information, where the received at least one piece of event detection information includes a magnitude level of a fault indicated by the fault flag and an initial confidence level;

generate at least one remanent confidence level value that decreases from the initial confidence level over time starting from the detection time, the remanent confidence level value being associated with the fault flag and the magnitude level associated with the received at least one piece of event detection information; and

when a new piece of event detection information is received that is associated with the fault flag and includes an initial confidence level and a same magnitude level as the at least one piece of event detection information, generate an integrated remanent confidence level value for the new piece of event detection information which is based on the initial confidence level that is included in the new piece of event detection information and the remanent confidence level value that exists at a time when the new piece of event detection information is received,

wherein the at least one piece of detection information associated with a detection time is included in a failure message including at least a failure time, the initial confidence level, and a failure identifier.

2. The sensor system according to claim 1, wherein the remanent confidence level value is associated with at least one failure magnitude value selected as a function of a failure magnitude value associated with the detection time.

3. The sensor system according to claim 1, wherein the processing circuitry is configured to generate at least two remanent confidence level values, each associated with a malfunction magnitude value, each of the at least two remanent confidence level values varying independently of the other.

4. The sensor system according to claim 1, wherein the processing circuitry is configured to generate at least two remanent confidence level values each associated with a different malfunction magnitude value, and reset to zero one of the at least two remanent confidence level values that was non-zero at a previous time when the other remanent confidence level value becomes non-zero at a current time.

5. The sensor system according to claim 1, wherein, the remanent confidence level value is a raw value.

6. The sensor system according to claim 1, wherein the initial confidence level and the raw remanent confidence level value are combined to give the integrated remanent confidence value by an addition.

7. The sensor system according to claim 1, wherein a duration from which the remanent confidence level value is zero may be set by a user, for a single fault flag, or for a plurality of fault flags.

8. The sensor system according to claim 1, wherein a decreasing relationship may be set by a user for the remanent confidence level value, for a single fault flag, or for a plurality of fault flags.

9. The sensor system according to claim 1, wherein the complex system is an engine.

10. An sensing method for monitoring a complex system, the method comprising:

detecting, by at least one sensor placed in a particular location in the complex system, one or more physical magnitudes whenever a variation is detected relative to a threshold

receiving at least one piece of event detection information from the at least one sensor associated with a detection time, a fault flag being associated with the at least one piece of event detection information, where the received at least one piece of event detection information includes a magnitude level of a fault indicated by the fault flag and an initial confidence level;

generating at least one remanent confidence level value that decreases from the initial confidence level over time starting from the detection time, the remanent confidence level value being associated with the fault flag and the magnitude level associated with the received at least one piece of event detection information; and

when a new piece of event detection information is received that is associated with the fault flag and includes an initial confidence level and a same magnitude level as the at least one piece of event detection information, generating an integrated remanent confidence level value for the new piece of event detection information which is based on the initial confidence level that is included in the new piece of event detection information and the remanent confidence level value that exists at a time when the new piece of event detection information is received,

wherein the at least one piece of detection information associated with a detection time is included in a failure message including at least a failure time, the initial confidence level, and a failure identifier.