Vehicle fault diagnosis and analysis based on augmented design failure mode and effect analysis (dfmea) data

Patent metadata

Field	Value
Publication number	US-2020394850-A1
Application number	US-201916443383-A
Country	US
Kind code	A1
Filing date	Jun 17, 2019
Priority date	Jun 17, 2019
Publication date	Dec 17, 2020
Grant date	—

Abstract

A system and method of performing fault diagnosis and analysis for one or more vehicles. The method includes: obtaining design failure mode and effect analysis (DFMEA) data that specifies a plurality of failure modes; receiving diagnostic association data; receiving vehicle operation signals association data; generating augmented DFMEA data that indicates a causal relationship between the diagnostic data and the first set of failure modes, and that indicates a causal relationship between the vehicle operation signals data and the second set of failure modes, wherein the augmented DFMEA data is generated based on the DFMEA data, the diagnostic association data, and the vehicle operation signals association data; and performing fault diagnosis and analysis for the one or more vehicles using the augmented DFMEA data.

First claim

What is claimed is:

1 . A method of performing fault diagnosis and analysis for one or more vehicles, comprising the steps of:
obtaining design failure mode and effect analysis (DFMEA) data, wherein the DFMEA data specifies a plurality of failure modes; receiving diagnostic association data, wherein the diagnostic association data specifies, for each of a first set of the plurality of failure modes, diagnostic data that is to be associated with the failure mode; receiving vehicle operation signals association data, wherein the vehicle operation signals association data specifies, for each of a second set of the plurality of failure modes, vehicle operation signals data that is to be associated with the failure mode; generating augmented DFMEA data that indicates a causal relationship between the diagnostic data and the first set of failure modes, and that indicates a causal relationship between the vehicle operation signals data and the second set of failure modes, wherein the augmented DFMEA data is generated based on the DFMEA data, the diagnostic association data, and the vehicle operation signals association data; and performing fault diagnosis and analysis for the one or more vehicles using the augmented DFMEA data.

2 . The method of claim 1 , wherein the DFMEA data includes or is based on a first DFMEA document that is generated as a part of designing, developing, manufacturing, and/or testing a first subsystem of the one or more vehicles, wherein the DFMEA data includes or is based on a second DFMEA document that is generated as a part of designing, developing, manufacturing, and/or testing a second subsystem of the one or more vehicles.

3 . The method of claim 2 , wherein the plurality of failure modes includes a plurality of first subsystem failure modes and a plurality of second subsystem failure modes, wherein the plurality of first subsystem failure modes specifies failure modes pertaining to the first subsystem, and wherein the plurality of second subsystem failure modes specifies failure modes pertaining to the second subsystem.

4 . The method of claim 3 , wherein the augmented DFMEA data includes a first augmented DFMEA document and a second augmented DFMEA document, wherein the first augmented DFMEA document indicates the causal relationship between the diagnostic data and a third set of failure modes, wherein the third set of failure modes are those failure modes that are a part of the first set of failure modes and the first subsystem failure modes, wherein the first augmented DFMEA document indicates the causal relationship between the vehicle operation signals data and a fourth set of failure modes, and wherein the fourth set of failure modes are those failure modes that are a part of the second set of failure modes and the first subsystem failure modes.

5 . The method of claim 4 , wherein the second augmented DFMEA document indicates the causal relationship between the diagnostic data and a fifth set of failure modes, wherein the fifth set of failure modes are those failure modes that are a part of the first set of failure modes and the second subsystem failure modes, wherein the second augmented DFMEA document indicates the causal relationship between the vehicle operation signals data and a sixth set of failure modes, and wherein the sixth set of failure modes are those failure modes that are a part of the second set of failure modes and the second subsystem failure modes.

6 . The method of claim 5 , further comprising the step of generating a dependency model based on the augmented DFMEA data, wherein the dependency model captures causal relationship(s) between the first subsystem failure modes and the second subsystem failure modes, and wherein the causal relationship(s) are identified based on the first augmented DFMEA document and the second augmented DFMEA document.

7 . The method of claim 1 , wherein the diagnostics association data is received from a first technical specialist at a first computer, and wherein the vehicle operation signals association data is received from a second technical specialist at a second computer.

8 . The method of claim 1 , wherein the fault diagnosis and analysis includes generating an artificial intelligence (AI) classifier based on the augmented DFMEA data.

9 . The method of claim 8 , wherein the fault diagnosis and analysis includes executing an AI computer application to diagnose the one or more vehicles based on observed diagnostic data and/or observed vehicle operation signals data pertaining to the one or more vehicles, and wherein the AI computer application is configured to use the AI classifier to diagnose the one or more vehicles.

10 . The method of claim 9 , further comprising the step of sending a message to at least one of the one or more vehicles, wherein the message indicates a particular failure mode of the plurality of failure modes that is identified based on the diagnosis performed using the AI computer application.

11 . The method of claim 1 , wherein the fault diagnosis and analysis includes determining whether each of the plurality of failure modes are isolatable from one another.

12 . A method of performing fault diagnosis and analysis for one or more vehicles, comprising the steps of:
obtaining design failure mode and effect analysis (DFMEA) data, wherein the DFMEA data specifies a plurality of failure modes including first subsystem failure modes and second subsystem failure modes; receiving diagnostic association data, wherein the diagnostic association data specifies, for each of a first set of the plurality of failure modes, one or more diagnostic trouble code(s) (DTC(s)) that are to be associated with the failure mode; receiving vehicle operation signals association data, wherein the vehicle operation signals association data specifies, for each of a second set of the plurality of failure modes, vehicle operation signals data that is to be associated with the failure mode; generating augmented DFMEA data that indicates the DTC(s) that are observable at the one or more vehicles when the one or more vehicles are experiencing any failure mode(s) of the first set of failure modes, and that indicates the vehicle operation signals data that is observable at the one or more vehicles when the one or more vehicles are experiencing any failure mode(s) of the second set of failure modes, wherein the augmented DFMEA data is generated based on the DFMEA data, the diagnostic association data, and the vehicle operation signals association data; generating a dependency model based on the augmented DFMEA data, wherein the dependency model indicates causal relationships between the first subsystem failure modes and the second subsystem failure modes; and performing fault diagnosis and analysis for the one or more vehicles using the augmented DFMEA data.

13 . The method of claim 12 , wherein the fault diagnosis and analysis includes: obtaining observed diagnostic data and observed vehicle operation signals data pertaining to at least one of the one or more vehicles, and identifying a failure mode of the at least one vehicle by comparing the observed diagnostic data to diagnostic data as indicated in the dependency model and by comparing the observed vehicle operation signals data to vehicle operation signals data as indicated in the dependency model.

14 . The method of claim 12 , wherein a first portion of the diagnostics association data is received from a first technical specialist at a first computer and a second portion of the diagnostics association data is received from a second technical specialist at a second computer.

Assignees

• Gm Global Tech Operations Llc

Inventors

• Sankavaram Chaitanya
• Rajpathak Dnyanesh G
• Sarwar Azeem
• Lu Xiangxing
• Sorrell Dean G
• Wiggins Layne K

Classifications

• G06N20/00

  Machine learning · CPC title

• G07C5/0808 Primary

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

• G07C5/008 Primary

  communicating information to a remotely located station (transmission systems for measured values G08C) · CPC title

• G07C5/02

  Registering or indicating driving, working, idle, or waiting time only (apparatus forming part of taximeters G07B13/00) · CPC title

• G07C5/08

  Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle or waiting time · CPC title