Model-based diagnostic interface for a vehicle health management system having a system model with a system nomeclature

• US 8,180,610 B2
• Filed: 10/08/2003
• Issued: 05/15/2012
• Est. Priority Date: 10/08/2003
• Status: Active Grant

• Current Assignee: Honeywell International Inc.
• Original Assignee: Honeywell International Inc.
• Inventors: Rachlin, Elliott, Blaser, Robert A., Kabbas, Ed, Boender, Mike, Aaseng, Gordon, Dopilka, Dave, Quinn, Ronald
• Primary Examiner(s): Rodriguez, Paul
• Assistant Examiner(s): Janakiraman, Nithya
• Application Number:
  US10/682,750
• Publication Number:
  US 20050080593A1
• Time in Patent Office: 3,142 Days
• Field of Search: 703/4, 714/46
• US Class Current: 703/4
• CPC Class Codes: G07C 5/008 communicating information to a remotely located station transmission systems for measured values G08C

Abstract

Methods and apparatus are provided for a model-based diagnostic interface. An apparatus is provided for a diagnostic interface for a system having system data, system information, and a system model having a model nomenclature, the diagnostic interface comprising at least one computational object producing an output responsive to said system data, wherein said at least one object includes a binding of said system data to said system information, wherein said system data is mapped to said model nomenclature before being bound. A method is provided for making a model-based diagnostic interface for a system having system information and system data representing the status of said system, the method comprising the steps of modeling said system to create a system model having a system model nomenclature, mapping said system data into said system model nomenclature, and binding said system data mapped to said system model nomenclature to said system information.

Claims

1. A method for evaluating one or more failures of a system having system information representing relationships within said system and system data representing the status of said system, the method comprising the steps of:

modeling a hierarchical system to include a model nomenclature representation of the system information, model information and nomenclature, system failure mode information and nomenclature, and telemetry information and nomenclature, using the system data;

mapping the system information, the model information and nomenclature, the system failure mode information and nomenclature, and the telemetry information and nomenclature into a binding function, using the model nomenclature representation;

binding the system information, the model information and nomenclature, the system failure mode information and nomenclature, and the telemetry information and nomenclature using the binding function, thereby generating a bound system;

generating an optimized model-based diagnostic interface for runtime execution, using the bound system;

determining one or more system failures, using the bound system and the optimized model-based diagnostic interface; and

determining a root cause of one or more of the systems failures, using the bound system and the optimized model-based diagnostic interface.

2. The method of claim 1, further comprising the steps of:

generating computational classes adapted for creating computational objects adapted for producing input data for at least one diagnostic engine from said system data;

selecting at least one pass/fail diagnostic engine from a plurality of diagnostic engines to receive inputs from said computational objects; and

selecting a subset of said system data based upon said selection of said at least one diagnostic engine.

3. The method of claim 1 wherein said system data has attributes, and the method further comprises the steps of:

associating said system data with one or more said attributes; and

associating at least one item of said system data with at least one respective corresponding element of said model nomenclature.

4. The method of claim 1, further comprising the steps of:

selecting a computational language; and

generating functions in said computational language which are executable to generate inputs for at least one diagnostic engine based at least in part on said system data.

5. The method of claim 1, further comprising the steps of:

generating test information for each modeled system component, the test information for each modeled system component comprising an output generated after providing a testing input to such modeled system component; and

associating each modeled system component with the test information for such modeled system component.

6. The method of claim 1, further comprising the step of:

predicting a future outcome, and a measure of impact of the future outcome, using the bound system and the model-based diagnostic interface.

7. The method of claim 1, wherein the model information comprises system component hierarchical information, system structural hierarchical information, and data schema information.

8. The method of claim 1, wherein the step of determining one or more system failures comprises the steps of:

identifying a plurality of failure modes in the system; and

selecting, from the failure modes, one or more likely failure modes corresponding to the system data, telemetry, and the bound system.

9. The method of claim 8, wherein the step of determining one or more root causes for each of the likely failure modes comprises the steps of:

determining one or more initial causes for one or more of the likely failure modes;

comparing the one or more initial causes to one or more likely causes; and

determining the one or more root causes, based on the comparison of the one or more initial causes to the one or more likely causes.

10. The method of claim 9, wherein the step of comparing the one or more initial causes to the one or more likely causes comprises using multiple methods that include at least one of the following:

historical data analysis, off-line reasoning, human analysis, and data mining techniques.

11. The method of claim 9, further comprising the steps of:

determining a measure of impact for one or more of the likely failure modes;

determining remaining system capabilities, based at least in part on the measure of impact; and

determining a recommended corrective action, based at least in part on the measure of impact and the remaining system capabilities.

12. The method of claim 11, further comprising the step of:

storing the following historical data;

one or more failure modes, one or more root causes, one or more measures of impact, the remaining system capabilities, and the recommended corrective action.

13. The method of claim 1, further comprising the steps of:

generating a model for each of a plurality of system components;

associating the plurality of modeled system components with one another; and

generating telemetry for, and associating the telemetry with, each modeled system component, the telemetry for each modeled system component comprising data indicating at least a status of the modeled system component.

14. An apparatus comprising:

(a) a processor;

(b) a memory coupled to the processor; and

(c) a program residing in the memory and executable by the processor, the program including a diagnostic interface for a system having system data representing a status of said system, system information relating to relationships within said system, and having a hierarchical system model that includes a model nomenclature representation of the system information, model information and nomenclature, system failure mode information and nomenclature, and telemetry information and nomenclature, the program configured to;

map the system information, the model information and nomenclature, the system failure mode information and nomenclature, and the telemetry information and nomenclature into a binding function, using the model nomenclature representation;

bind the system information, the model information and nomenclature, the system failure mode information and nomenclature, and the telemetry information and nomenclature using the binding function, to thereby generate a bound system;

generate an optimized model-based diagnostic interface for runtime execution, using the bound system;

determine one or more system failures, using the bound system and the optimized model-based diagnostic interface; and

determine a root cause of one or more of the systems failures, using the bound system and the optimized model-based diagnostic interface.

15. The apparatus of claim 14, further comprising an input coupling to a source of said system data.

16. The apparatus of claim 14, wherein the model nomenclature comprises a language for expressing a system in a systems modeling environment, said language comprising tokens that can be manipulated by modeling software, wherein said tokens include at least one of an icon, a variable name, an element name, a component name, a format, and a relationship identifier.

17. The apparatus of claim 14, wherein the program is further configured to:

predict a future outcome, and a measure of impact of the future outcome, using the bound system and the model-based diagnostic interface.

18. The apparatus of claim 14, wherein the model information comprises system component hierarchical information, system structural hierarchical information, and data schema information.

19. The apparatus of claim 14, wherein the program is further configured to:

identify a plurality of failure modes in the system; and

select, from the failure modes, one or more likely failure modes corresponding to the system data, telemetry, and the bound system.

20. The apparatus of claim 14, wherein the program is further configured to:

determine one or more initial causes for one or more likely failure modes;

compare the one or more initial causes to one or more likely causes; and

determine the one or more root causes, based on the comparison of the one or more initial causes to the one or more likely causes.

21. The apparatus of claim 14, wherein the program is configured to compare one or more initial causes to one or more likely causes using multiple methods that include at least one of the following:

historical data analysis, off-line reasoning, human analysis, and data mining techniques.

22. The apparatus of claim 14, wherein the program is further configured to:

determine a measure of impact for one or more of the likely failure modes;

determine remaining system capabilities, based at least in part on the measure of impact; and

determine a recommended corrective action, based at least in part on the measure of impact and the remaining system capabilities.

23. The apparatus of claim 14, wherein the diagnostic interface comprises at least one computational object producing an output responsive to said system data, wherein said at least one computational object includes a binding to said system information of said system data mapped to said model nomenclature.

24. The apparatus of claim 14, wherein the hierarchical system model includes an association of a plurality of modeled system components with one another, and an association of each modeled system component with telemetry, the telemetry associated with each modeled system component comprising data indicating the status of the modeled system component.

25. A program product comprising:

a model-based diagnostic interface program comprising at least one object binding mapped system data to system information relating to relationships within said system, wherein said mapped system data includes system data that has been mapped to a model nomenclature of a hierarchical model of said system, said at least one object executable to produce an input to a diagnostic engine responsive to system data, the hierarchical system model including a model nomenclature representation of the system information, model information and nomenclature, system failure mode information and nomenclature, and telemetry information and nomenclature, the model-based diagnostic interface program configured to;

map the system information, the model information and nomenclature, the system failure mode information and nomenclature, and the telemetry information and nomenclature into a binding function, using the model nomenclature representation;

bind the system information, the model information and nomenclature, the system failure mode information and nomenclature, and the telemetry information and nomenclature using the binding function, to thereby generate a bound system;

generate an optimized model-based diagnostic interface for runtime execution, using the bound system;

determine one or more system failures, using the bound system and the optimized model-based diagnostic interface; and

determine a root cause of one or more of the systems failures, using the bound system and the optimized model-based diagnostic interface; and

a non-transitory computer-readable media bearing the model-based diagnostic interface program.

26. The program product of claim 25, wherein said at least one object is linkable to an integrated vehicle health management system.

27. The program product of claim 25, wherein the model nomenclature comprises a language for expressing a system in a systems modeling environment, said language comprising tokens that can be manipulated by modeling software, wherein said tokens include at least one of an icon, a variable name, an element name, a component name, a format, and a relationship identifier.

28. The program product of claim 25, wherein the model information comprises system component hierarchical information, system structural hierarchical information, and data schema information.

29. The program product of claim 25, wherein the model-based diagnostic interface program is further configured to:

identify a plurality of failure modes in the system; and

select, from the failure modes, one or more likely failure modes corresponding to the system data, telemetry, and the bound system.

30. The program product of claim 25, wherein the model-based diagnostic interface program is further configured to:

determine one or more initial causes for one or more likely failure modes;

compare the one or more initial causes to one or more likely causes; and

determine the one or more root causes, based on the comparison of the one or more initial causes to the one or more likely causes.

31. The program product of claim 25, wherein the model-based diagnostic interface program is configured to compare the one or more initial causes to one or more likely causes using multiple methods that include at least one of the following:

historical data analysis, off-line reasoning, human analysis, and data mining techniques.

32. The program product of claim 25, wherein the model-based diagnostic interface program is further configured to:

determine a measure of impact for one or more of likely failure modes;

determine remaining system capabilities, based at least in pa part on the measure of impact; and

determine a recommended corrective action, based at least in part on the measure of impact and the remaining system capabilities.