System and method for automatic generation of a diagnostic model

• US 11,055,161 B2
• Filed: 04/18/2018
• Issued: 07/06/2021
• Est. Priority Date: 04/18/2018
• Status: Active Grant

• Current Assignee: Honeywell International Inc.
• Original Assignee: Honeywell International Inc.
• Inventors: Venkataswamy, Sadguni, Halappa, Kiran Kumar H
• Primary Examiner(s): McPherson, James M
• Application Number:
  US15/955,933
• Publication Number:
  US 20190324837A1
• Time in Patent Office: 1,175 Days
• Field of Search: 701 318
• CPC Class Codes: B64D 2045/0085 Devices for aircraft health monitoring, e.g. monitoring flutter or vibration
• CPC Class Codes: B64F 5/40 Maintaining or repairing aircraft
• CPC Class Codes: B64F 5/60 Testing or inspecting aircraft components or systems
• CPC Class Codes: G06F 11/0739 in a data processing system embedded in automotive or aircraft systems
• CPC Class Codes: G06F 11/079 Root cause analysis, i.e. error or fault diagnosis in a hardware test environment G06F11/22; in a software test environment G06F11/36
• CPC Class Codes: G06F 11/0793 Remedial or corrective actions recovery from an exception in an instruction pipeline G06F9/3861; by retry G06F11/1402; for recovering from a failure of a protocol instance or entity H04L69/40

Abstract

A cloud-based computing system for providing a maintenance message associated with a unique maintenance action for fault rectification is disclosed. The system includes a diagnostic module including one or more processors configured by instructions stored in non-transient computer readable media. The diagnostic module is configured to: identify, for each potential CAS message in an aircraft, a set of inputs that are evaluated to trigger the potential CAS message; identify, for each of the potential CAS messages, each unique combination of input conditions for the set of inputs that triggers the potential CAS message; and identify, for each of the potential CAS messages, a unique maintenance message associated with each unique combination of input conditions that triggers the potential CAS message, wherein each unique maintenance message is associated with a unique maintenance action for fault rectification.

Claims

1. A computing system, the computing system comprising:

at least one memory storing instructions; and

at least one processor being configured to execute the instructions to perform operations, the operations including;

receiving a crew alerting system (CAS) message or a query regarding the CAS message, the CAS message being triggered in relation to an aircraft;

responsive to receiving the CAS message or the query, selecting an aircraft-specific diagnostic model corresponding to the aircraft, from among a plurality of aircraft-specific diagnostic models;

identifying, using the selected aircraft-specific diagnostic model, a set of inputs known to trigger the CAS message in relation to the aircraft;

retrieving aircraft data regarding the aircraft that includes a condition for each input of the set of inputs known to trigger the CAS message;

identifying, using the selected aircraft-specific diagnostic model and the retrieved aircraft data, a unique combination of input conditions that triggered the CAS message for the aircraft;

identifying a unique maintenance message associated with the unique combination of input conditions that triggered the CAS message, the unique maintenance message identifying a unique maintenance action that rectifies a fault corresponding to the unique combination of input conditions; and

transmitting or displaying the unique maintenance message that identifies the unique maintenance action that rectifies the fault.

2. The computing system of claim 1, wherein The computing system of claim 1, wherein identifying the unique maintenance message includes invoking a diagnostic module, the diagnostic module is configured to identify maintenance messages by:

identifying, for each of a plurality of potential CAS messages in the aircraft, a set of inputs that are evaluated to trigger a specific potential CAS message;

identifying, for each of the plurality of potential CAS messages, a corresponding set of input conditions for the set of inputs that triggers the specific potential CAS message;

identifying, for each of the plurality of potential CAS messages, a maintenance message associated with the corresponding set of input conditions for the set of inputs that triggers the specific potential CAS message; and

identifying, for each of the plurality of potential CAS messages, logic applied to the set of inputs to trigger the specific potential CAS message, the logic being used to identify the unique combination of input conditions that triggered the CAS message.

3. The computing system of claim 1, wherein identifying the unique combination of input conditions that triggered the CAS message includes applying a machine learning model to identify the unique combination of input conditions.

4. The computing system of claim 1, wherein the operations further include generating the plurality of aircraft-specific diagnostic models using machine learning model(s) to learn and identify, for each of a plurality of potential CAS messages, a combination of input conditions that triggered a specific potential CAS message.

5. The computing system of claim 1, wherein retrieving aircraft data includes receiving aircraft bus data from the aircraft as the aircraft data.

6. The computing system of claim 1, wherein the operations further include generating the plurality of aircraft-specific diagnostic models a CAS logic input.

7. The computing system of claim 1, wherein the operations further include generating the plurality of aircraft-specific diagnostic models externally to a diagnostic module and then input to the diagnostic module.

8. The computing system of claim 4, wherein the plurality of aircraft-specific diagnostic models that have been generated using the machine learning model(s) are generated externally to a diagnostic module and input to the diagnostic module.

9. A computer-implemented method comprising:

receiving a crew alerting system (CAS) message or a query regarding the CAS message, the CAS message being triggered in relation to an aircraft;

responsive to receiving the CAS message or the query, selecting an aircraft-specific diagnostic model corresponding to the aircraft, from among a plurality of aircraft-specific diagnostic models;

identifying, using the selected aircraft-specific diagnostic model, a set of inputs known to trigger the CAS message in relation to the aircraft;

retrieving aircraft data regarding the aircraft that includes a condition for each input of the set of inputs known to trigger the CAS message;

identifying, using the selected aircraft-specific diagnostic model and the retrieved aircraft data, a unique combination of input conditions that triggered the CAS message for the aircraft;

identifying a unique maintenance message associated with the unique combination of input conditions that triggered the CAS message, the unique maintenance message identifying a unique maintenance action that rectifies a fault corresponding to the unique combination of input conditions; and

transmitting or displaying the unique maintenance message that identifies the unique maintenance action that rectifies the fault.

10. The computer-implemented method of claim 9, wherein identifying the unique maintenance message includes invoking a diagnostic module, the diagnostic module is configured to identify maintenance messages by:

identifying, for each of a plurality of potential CAS messages in the aircraft, a set of inputs that are evaluated to trigger a specific potential CAS message;

identifying, for each of the plurality of potential CAS messages, a corresponding set of input conditions for the set of inputs that triggers the specific potential CAS message;

identifying, for each of the plurality of potential CAS messages, a maintenance message associated with the corresponding set of input conditions for the set of inputs that triggers the specific potential CAS message; and

identifying, for each of the plurality of potential CAS messages, logic applied to the set of inputs to trigger the specific potential CAS message, the logic being used to identify the unique combination of input conditions that triggered the CAS message.

11. The computer-implemented method of claim 9, wherein identifying the unique combination of input conditions that triggered the CAS message includes applying a machine learning model to identify the unique combination of input conditions.

12. The computer-implemented method of claim 9, further comprising generating the plurality of aircraft-specific diagnostic models using machine learning model(s) to learn and identify, for each of a plurality of potential CAS messages, a combination of input conditions that triggered a specific potential CAS message.

13. The computer-implemented method of claim 9, wherein retrieving aircraft data includes receiving aircraft bus data from the aircraft as the aircraft data.

14. The computer-implemented method of claim 9, further comprising generating the plurality of aircraft-specific diagnostic models a CAS logic input.

15. The computer-implemented method of claim 9, further comprising generating the plurality of aircraft-specific diagnostic models externally to a diagnostic module and then input to the diagnostic module.

16. The computer-implemented method of claim 12, wherein the plurality of aircraft-specific diagnostic models that have been generated using the machine learning model(s) are generated externally to a diagnostic module and input to the diagnostic module.

17. A non-transitory computer-readable medium storing instructions that, when executed by a processor, cause the processor to perform a method, the method comprising:

receiving a crew alerting system (CAS) message or a query regarding the CAS message, the CAS message being triggered in relation to an aircraft;

responsive to receiving the CAS message or the query, selecting an aircraft- specific diagnostic model corresponding to the aircraft, from among a plurality of aircraft-specific diagnostic models;

identifying, using the selected aircraft-specific diagnostic model, a set of inputs known to trigger the CAS message in relation to the aircraft;

retrieving aircraft data regarding the aircraft that includes a condition for each input of the set of inputs known to trigger the CAS message;

identifying, using the selected aircraft-specific diagnostic model and the retrieved aircraft data, a unique combination of input conditions that triggered the CAS message for the aircraft;

identifying a unique maintenance message associated with the unique combination of input conditions that triggered the CAS message, the unique maintenance message identifying a unique maintenance action that rectifies a fault corresponding to the unique combination of input conditions; and

transmitting or displaying the unique maintenance message that identifies the unique maintenance action that rectifies the fault.

18. The non-transitory computer-readable medium of claim 17, wherein identifying the unique maintenance message includes invoking a diagnostic module, the diagnostic module is configured to identify maintenance messages by:

identifying, for each of a plurality of potential CAS messages in the aircraft, a set of inputs that are evaluated to trigger a specific potential CAS message;

identifying, for each of the plurality of potential CAS messages, a corresponding set of input conditions for the set of inputs that triggers the specific potential CAS message;

identifying, for each of the plurality of potential CAS messages, a maintenance message associated with the corresponding set of input conditions for the set of inputs that triggers the specific potential CAS message; and

identifying, for each of the plurality of potential CAS messages, logic applied to the set of inputs to trigger the specific potential CAS message, the logic being used to identify the unique combination of input conditions that triggered the CAS message.

19. The non-transitory computer-readable medium of claim 17, wherein identifying the unique combination of input conditions that triggered the CAS message includes applying a machine learning model to identify the unique combination of input conditions.

20. The non-transitory computer-readable medium of claim 17, wherein the method further includes generating the plurality of aircraft-specific diagnostic models using machine learning model(s) to learn and identify, for each of a plurality of potential CAS messages, a combination of input conditions that triggered a specific potential CAS message.