Method of fault isolation for systems with existing diagnostics

Patent metadata

Field	Value
Publication number	US-10975794-B2
Application number	US-201816616274-A
Country	US
Kind code	B2
Filing date	May 25, 2018
Priority date	May 26, 2017
Publication date	Apr 13, 2021
Grant date	Apr 13, 2021

Abstract

A method ( 50 ) for isolating a fault within an engine system ( 10 ) including an engine control module ( 40 ) and a diagnostics module ( 36 ) includes determining, by the engine control module ( 40 ), a plurality of parameters of the engine system ( 10 ), calculating a likelihood of the fault using a log-likelihood ratio analysis of data within the engine control module ( 40 ), and providing a plurality of fault determinations and the likelihood of each of the plurality of fault determinations using plurality of parameters and the diagnostics module ( 36 ) of the engine system ( 10 ).

First claim

What is claimed is:

1. A method for isolating a fault within an engine system including an engine control module and a diagnostics module, comprising:
determining, by the engine control module, a plurality of parameters of the engine system;
calculating a likelihood of a fault using a log-likelihood ratio analysis of data within the engine control module, the log-likelihood-ratio analysis being performed using a plurality of weighting vectors, at least some of the plurality of weighting vectors being associated with at least one failure mode detected in the engine system;
providing a plurality of fault determinations and the likelihood of each of the plurality of fault determinations using the plurality of parameters and the diagnostics module of the engine system; and
controlling the engine system based on the likelihood of each of the plurality of fault determinations.

2. The method of claim 1 , wherein the plurality of parameters of the engine system are determined during operation of the engine system, and further comprising comparing the plurality of parameters to predetermined threshold parameters for the engine system.

3. The method of claim 2 , further comprising:
normalizing the plurality of parameters using a statistical analysis;
filtering the normalized plurality of parameters based on data from the diagnostics module;
calculating the likelihood of the fault using the log-likelihood ratio analysis for each possible failure mode of the engine system;
comparing the likelihoods for each of the possible failure modes; and
providing instructions to address the possible failure modes with highest likelihoods.

4. The method of claim 3 , wherein providing instructions includes visually displaying the possible failure modes with the highest likelihoods on a display.

5. The method of claim 4 , wherein the display is present on at least one the engine system and an external tool.

6. A method of isolating a fault within an engine system, comprising:
receiving a plurality of input parameters from the engine system;
receiving a plurality of threshold values from the engine system;
calculating a plurality of average values and a plurality of weighting vectors based on the plurality of input parameters, at least some of the plurality of weighting vectors being associated with at least one failure mode detected in the engine system;
calculating a log-likelihood ratio for each of a plurality of failure modes detected in the engine system based on the plurality of input parameters, the plurality of average values, and the plurality of weighting vectors;
comparing, using the log-likelihood ratio, the plurality of input parameters to the plurality of threshold values;
determining the fault of the engine system by calculating a probability of each of the plurality of failure modes detected in the engine system based on the comparison between the plurality of input parameters and the plurality of threshold values; and
controlling the engine system based on the probability of each of the plurality of failure modes detected in the engine system.

7. The method of claim 6 , further comprising normalizing the plurality of input parameters using a statistical analysis to account for one or more inconsistencies.

8. The method of claim 6 , further comprising applying at least one filter to at least one of: the plurality of input parameters and the plurality of threshold values to narrow a list of possible failure modes.

9. The method of claim 8 , wherein applying the at least one filter comprises applying a first filter to at least one of: the plurality of input parameters and the plurality of threshold values based on an operating condition of the engine system to remove one or more irrelevant failure modes.

10. The method of claim 8 , wherein applying the at least one filter comprises applying a second filter to at least one of: the plurality of input parameters and the plurality of threshold values based on values associated with an incomplete diagnostic process performed in the engine system.

11. The method of claim 6 , further comprising ranking the probability of each of the plurality of failure modes based on the log-likelihood ratio calculated for a corresponding failure mode.

12. The method of claim 11 , further comprising providing at least one instruction for correcting the fault of the engine system based on the probability ranking of each of the plurality of failure modes detected in the engine system.

13. The method of claim 12 , wherein providing the at least one instruction comprises displaying the at least one instruction on a display device.

14. The method of claim 12 , wherein providing the at least one instruction comprises transmitting the at least one instruction to a relevant party associated with the engine system.

15. A diagnostic system of isolating a fault within an engine system, comprising:
an engine control module configured to:
receive a plurality of input parameters from the engine system;
receive a plurality of threshold values from the engine system; and

an engine diagnostic module configured to:
calculate a plurality of average values and a plurality of weighting vectors based on the plurality of input parameters, at least some of the plurality of weighting vectors being associated with at least one failure mode detected in the engine system;
calculate a log-likelihood ratio for each of a plurality of failure modes detected in the engine system based on the plurality of input parameters, the plurality of average values, and the plurality of weighting vectors;
compare, using the log-likelihood ratio, the plurality of input parameters to the plurality of threshold values;
determine the fault of the engine system by calculating a probability of each of the plurality of failure modes detected in the engine system based on the comparison between the plurality of input parameters and the plurality of threshold values; and
control the engine system based on the probability of each of the plurality of failure modes detected in the engine system.

16. The system of claim 15 , wherein the engine diagnostic module is further configured to normalize the plurality of input parameters using a statistical analysis to account for one or more inconsistencies.

17. The system of claim 15 , wherein the engine diagnostic module is further configured to apply at least one filter to at least one of: the plurality of input parameters and the plurality of threshold values to narrow a list of possible failure modes.

18. The system of claim 17 , wherein the engine diagnostic module is further configured to apply a first filter to at least one of: the plurality of input parameters and the plurality of threshold values based on an operating condition of the engine system to remove one or more irrelevant failure modes.

19. The system of claim 17 , wherein the engine diagnostic module is further configured to apply a second filter to at least one of: the plurality of input parameters and the plurality of threshold values based on values associated with an incomplete diagnostic process performed in the engine system.

20. The system of claim 15 , wherein the engine diagnostic module is further configured to rank the probability of each of the plurality of failure modes based on the log-likelihood ratio calculated for a corresponding failure mode.

Assignees

• Cummins Inc

Inventors

• Smith Daniel J

Classifications

• G07C5/0816

  Indicating performance data, e.g. occurrence of a malfunction · CPC title

• G07C5/0808

  Diagnosing performance data (testing of vehicles G01M17/00; testing of electrical installation on vehicles G01R31/005) · CPC title

• F02D41/221 Primary

  relating to the failure of actuators or electrically driven elements · CPC title

• F02D2041/224

  Diagnosis of the fuel system · CPC title

• G07C5/0841

  Registering performance data (recording measured values G01D; information storage G11B) · CPC title