Systems and methods for health monitoring of complex systems

• US 8,437,904 B2
• Filed: 09/28/2007
• Issued: 05/07/2013
• Est. Priority Date: 06/12/2007
• Status: Active Grant

• Current Assignee: The Boeing Co.
• Original Assignee: The Boeing Co.
• Inventors: Mansouri, Ali R., Vian, John L., Przytula, Krzysztof Wojtek, Allen, David
• Primary Examiner(s): Shafi, Muhammad
• Application Number:
  US11/864,717
• Publication Number:
  US 20080312783A1
• Time in Patent Office: 2,048 Days
• Field of Search: 701 1- 18, 701/29, 701/30, 701/34, 701/45, 701/46, 701/49, 701/59, 701/103, 701/104, 701/108, 701/112, 455/345, 731/78.R, 702/181, 702/183, 702/3, 702/179, 713/300, 342/63, 342/385, 324/500, 700/79, 705/7
• US Class Current: 701/29.1
• CPC Class Codes: G07C 5/0808 Diagnosing performance data testing of vehicles G01M17/00; testing of electrical installation on vehicles G01R31/005
• CPC Class Codes: G07C 5/0816 Indicating performance data, e.g. occurrence of a malfunction

Abstract

Systems and methods for health monitoring of complex systems are disclosed. In one embodiment, a method includes receiving a plurality of signals indicative of observation states of plurality of operating variables, performing a combined probability analysis of the plurality of signals using a diagnostic model of a monitored system to provide a health prognosis of the monitored system, and providing an indication of the health prognosis of the monitored system. In some embodiments, the monitored system may be an onboard system of an aircraft.

Claims

1. A method to evaluate a condition of an aircraft engine precooler, comprising:

receiving, in a processor-based health management system, a plurality of raw signals indicative of observation states of a plurality of operating variables associated with the aircraft engine precooler;

smoothing the plurality of raw signals collected during a flight to obtain a per-flight diagnosis;

performing, in the processor-based health management system, a joint probability analysis of the plurality of signals using a diagnostic model to generate a predictive failure prediction for the aircraft engine precooler; and

reporting the predictive failure prediction to an aircraft health management system, wherein performing, in the processor-based health management system, a joint probability analysis of the plurality of signals using a diagnostic model to generate a predictive failure prediction for the aircraft engine precooler comprises;

identifying a plurality of predictor nodes in a predictive failure model; and

evaluating a predictive probability of failure based on the plurality of predictor nodes.

2. The method of claim 1, wherein the plurality of signals comprise signals received from at least one of a pre-cooler high pressure shutoff (HPS) valve control system, a pre-cooler fan air modulating (FAM) valve control system, a pre-cooler pressure regulating and shutoff (PRS) valve control system, or ECS pre-cooler control logic.

3. The method of claim 2, wherein at least some of the signals are collected in real-time during operation of the aircraft engine precooler.

4. The method of claim 1, further comprising, prior to performing a joint probability analysis, developing a diagnostic model of the monitored system that determines a probability of failure based on one or more observation states of the plurality of operating variables.

5. The method of claim 4, wherein the knowledge of the monitored system includes at least one of a component reliability and a component weighting factor of a component of the monitored system.

6. The method of claim 1, wherein performing a joint probability analysis of the plurality of signals includes performing a joint probability analysis of the plurality of signals using a Bayesian network.

7. The method of claim 6, wherein performing a joint probability analysis includes performing a joint probability analysis to determine a probability of component failure based on a joint probability distribution over the plurality of signals indicative of observation states of the plurality of operating variables.

8. The method of claim 7, wherein the Bayesian network comprises a layered Bayesian network.

9. The method of claim 1, wherein receiving a plurality of signals includes receiving operational data from the monitored aircraft system.

10. The method of claim 1, wherein the onboard system of the aircraft includes an engine bleed pre-cooler of an environmental control system, the method further comprising predicting a failure of the pre-cooler based on a change in at least one of an average deviation in fuel flow, an average deviation in exhaust gas temperature (EGT), and an average deviation in air supply and control system (ASCS) temperature.

11. The method of claim 1 embodied in computer-readable instructions at least one of stored on a computer-readable storage medium and transmitted in real time.

12. A processor-based system to evaluate a condition of an aircraft engine precooler, comprising:

an input component configured to receive a plurality of raw signals associated with the aircraft engine precooler indicative of observation states of a plurality of operating variables; and

an analysis component coupled to the input component and configured to;

smooth the plurality of raw signals collected during a flight to obtain a per-flight diagnosis;

perform a joint probability analysis of the plurality of signals using a diagnostic model to generate a predictive failure prediction for the aircraft engine precooler; and

report the predictive failure prediction to an aircraft health management system;

identify a plurality of predictor nodes in a predictive failure model; and

evaluate a predictive probability of failure based on the plurality of predictor nodes.

13. The system of claim 12, wherein the plurality of signals comprise signals received from at least one of a pre-cooler high pressure shutoff (HPS) valve control system, a pre-cooler fan air modulating (FAM) valve control system, a pre-cooler pressure regulating and shutoff (PRS) valve control system, or ECS pre-cooler control logic.

14. The system of claim 13, wherein at least some of the signals are collected in real-time during operation of the aircraft engine precooler.

15. The system of claim 12, wherein the analysis component is further configured to perform the joint probability analysis using a Bayesian network.

16. The system of claim 12, wherein the monitored system includes an engine bleed pre-cooler of an aircraft environmental control system, and wherein the analysis component in further configured to predict a failure of the pre-cooler based on a change in at least one of an average deviation in fuel flow, an average deviation in exhaust gas temperature (EGT), and an average deviation in air supply and control system (ASCS) temperature.