DETECTING ANOMALIES IN FAULT CODE SETTINGS AND ENHANCING SERVICE DOCUMENTS USING ANALYTICAL SYMPTOMS

• US 20120303205A1
• Filed: 05/25/2011
• Published: 11/29/2012
• Est. Priority Date: 05/25/2011
• Status: Active Grant

• Current Assignee: GM Global Technology Operations LLC (General Motors Company)
• Original Assignee: GM Global Technology Operations LLC (General Motors Company)
• Inventors: Subramania, Halasya Siva, Singh, Satnam, Pinion, Clifton L.
• Granted Patent: US 8,509,985 B2
• Time in Patent Office: Days
• US Class Current: 701/29.8
• CPC Class Codes: G05B 23/0278 Qualitative, e.g. if-then rules; Fuzzy logic; Lookup tables; Symptomatic search; FMEA

Abstract

A method is provided for identifying a root cause of a fault in a serviced vehicle based on analytical symptoms. Parameter identification data associated with identified DTCs is retrieved. Parameter identification data from a plurality of vehicles experiencing the DTCs is collected. A first set of diagnostic rules is generated that identify vehicle operating parameters for executing a DTC algorithm or for triggering a DTC. A second set of diagnostic rules is generated that identify vehicle operating parameters used for selecting field failure data obtained when the DTC is triggered. Statistically significant rules are extracted from the second set of diagnostic rules. The first set of rules and the statistically significant rules are cooperatively applied to the parameter identification data for identifying a subset of the parameter identification data that represents anomalies. A subject matter expert analyzes the anomalies for identifying a root cause of the fault.

Claims

1. A method for identifying a root cause of a fault in a serviced vehicle based on anomalies identified in parameter identification data and performing corrective actions, the method comprising the steps of:

executing a diagnostic software routine for retrieving diagnostic trouble codes used to identify faults in an operation of the serviced vehicle;

retrieving parameter identification data associated with the diagnostic trouble codes identified with a detected fault;

collecting on a computer parameter identification data from a plurality of vehicles experiencing the diagnostic trouble codes;

generating a first set of diagnostic rules, the first set of diagnostic rules identifying vehicle operating parameters for executing a diagnostic trouble code algorithm or for triggering a diagnostic trouble code;

generating a second set of diagnostic rules, the second set of diagnostic rules identifying vehicle operating parameters used for selecting field failure data obtained when the diagnostic trouble code is triggered;

extracting statistically significant rules from the second set of diagnostic rules;

applying each of the first set of rules and the statistically significant rules cooperatively to the parameter identification data for identifying a subset of the parameter identification data that represents anomalies;

a subject matter expert analyzing the anomalies for identifying a root cause of the fault; and

performing corrective actions based on the identified root cause analysis.

2. The method of claim 1 wherein the first set of diagnostic rules is derived from at least one design-related document source.

3. The method of claim 1 wherein the second set of diagnostic rules is derived from a classifier.

4. The method of claim 1 wherein the second set of diagnostic rules is derived from a decision tree.

5. The method of claim 1 wherein the statistically significant rules are extracted using a classification accuracy technique, wherein the classification accuracy technique determines if a respective rule classifies a number of incidents relating to a single DTC greater than a classification threshold.

6. The method of claim 5 wherein the determination for identifying whether a statistically significant rule satisfies a respective class is represented by the following equation:

7. The method of claim 1 wherein the statistically significant rules are extracted using a population percentage technique, wherein the population percentage technique determines if a number of instances of a single diagnostic trouble code class as classified by a respective rule satisfies a population threshold in comparison to the total number of instances of diagnostic trouble code class.

8. The method of claim 7 wherein the determination for identifying whether a statistically significant rule satisfies a population threshold is represented by the following equation:

9. The method of claim 1 wherein the step of performing a corrective action includes modifying at least one of the diagnostic software routine for assessing diagnostic trouble codes.

10. The method of claim 1 wherein the step of performing a corrective action includes revising a service document used to by a service technician for assessing the fault.

11. The method of claim 1 wherein the step of performing a corrective action includes modifying a diagnostic software routine for triggering the diagnostic trouble code.

12. The method of claim 1 wherein the step of performing a corrective action includes revising a component in the vehicle that relates to fault.

13. The method of claim 1 wherein the step of performing a corrective action includes modifying a system associated that relates to the fault.