公开(公告)号：US20210056780A1

公开(公告)日：2021-02-25

申请号：US16548157

申请日：2019-08-22

Applicant: GM Global Technology Operations LLC

Inventor： Chaitanya Sankavaram ,  Shiming Duan ,  Xiaomeng Peng

IPC: G07C5/08 ,  G06K9/62 ,  G06N20/10 ,  G07C5/00

Abstract: A method of using an adaptive fault diagnostic system for motor vehicles is provided. A diagnostic tool collects unlabeled data associated with a motor vehicle, and the unlabeled data is transmitted to a central computer. An initial diagnostic model and labeled training data associated with previously identified failure modes and known health conditions are transmitted to the central computer. The central computer executes a novelty detection technique to determine whether the unlabeled data is novelty data corresponding with a new failure mode or normal data corresponding with one of the previously identified failure modes or known health conditions. The central computer selects an informative sample from the novelty data. A repair technician inputs a label for the informative sample, and the central computer propagates the label from the informative sample to the associated novelty data. The central computer updates the labeled training data to include the labeled novelty data.

公开(公告)号：US11981228B2

公开(公告)日：2024-05-14

申请号：US17698204

申请日：2022-03-18

Applicant: GM GLOBAL TECHNOLOGY OPERATIONS LLC

Inventor： Shiming Duan ,  Chaitanya Sankavaram ,  Xiaomeng Peng

IPC: B60L58/16 ,  G01R31/367 ,  G01R31/392

CPC classification number: B60L58/16 ,  G01R31/367 ,  G01R31/392

Abstract: A system for monitoring a battery assembly includes a processing device configured to receive measurement data from a plurality of battery components, and input the measurement data to a battery model configured to determine parametric data. Based on the battery model, the processing device is configured to acquire the parametric data, extract statistical information based on at least one parameter of each battery component, and input the statistical information to a failure identification module that includes a first classifier configured to determine whether the battery assembly is in a failure condition based on the statistical information. The processing device is configured to output a health indicator having a first value indicating that the battery assembly is healthy based on first classifier determining that the battery assembly is in the healthy condition, and a faulty value based on the first classifier determining that the battery assembly is in a failure condition.

公开(公告)号：US20230282033A1

公开(公告)日：2023-09-07

申请号：US17687221

申请日：2022-03-04

Applicant: GM GLOBAL TECHNOLOGY OPERATIONS LLC ,  NORTHEASTERN UNIVERSITY

Inventor： Shiming Duan ,  Yingjie Cai ,  Paul R. Hozak ,  Fernando Ferreira Pio ,  Gregory Sapick ,  Xiaomeng Peng

IPC: G07C5/00

CPC classification number: G07C5/006

Abstract: A system for validating diagnostic trouble codes (DTCs) in vehicles includes a processor and a memory storing instructions which when executed by the processor configure the processor to receive DTC data from the vehicles, filter the DTC data using predefined rules, generate one or more metrics based on the filtered DTC data, and determining based on the metrics whether the DTCs meet specifications for the DTCs.

公开(公告)号：US20230294554A1

公开(公告)日：2023-09-21

申请号：US17698204

申请日：2022-03-18

Applicant: GM GLOBAL TECHNOLOGY OPERATIONS LLC

Inventor： Shiming Duan ,  Chaitanya Sankavaram ,  Xiaomeng Peng

IPC: B60L58/16 ,  G01R31/367 ,  G01R31/392

CPC classification number: B60L58/16 ,  G01R31/367 ,  G01R31/392

Abstract: A system for monitoring a battery assembly includes a processing device configured to receive measurement data from a plurality of battery components, and input the measurement data to a battery model configured to determine parametric data. Based on the battery model, the processing device is configured to acquire the parametric data, extract statistical information based on at least one parameter of each battery component, and input the statistical information to a failure identification module that includes a first classifier configured to determine whether the battery assembly is in a failure condition based on the statistical information. The processing device is configured to output a health indicator having a first value indicating that the battery assembly is healthy based on first classifier determining that the battery assembly is in the healthy condition, and a faulty value based on the first classifier determining that the battery assembly is in a failure condition.

公开(公告)号：US11551488B2

公开(公告)日：2023-01-10

申请号：US16548157

申请日：2019-08-22

Applicant: GM Global Technology Operations LLC

Inventor： Chaitanya Sankavaram ,  Shiming Duan ,  Xiaomeng Peng

IPC: G07C5/08 ,  G06K9/62 ,  G07C5/00 ,  G06N20/10

Abstract: A method of using an adaptive fault diagnostic system for motor vehicles is provided. A diagnostic tool collects unlabeled data associated with a motor vehicle, and the unlabeled data is transmitted to a central computer. An initial diagnostic model and labeled training data associated with previously identified failure modes and known health conditions are transmitted to the central computer. The central computer executes a novelty detection technique to determine whether the unlabeled data is novelty data corresponding with a new failure mode or normal data corresponding with one of the previously identified failure modes or known health conditions. The central computer selects an informative sample from the novelty data. A repair technician inputs a label for the informative sample, and the central computer propagates the label from the informative sample to the associated novelty data. The central computer updates the labeled training data to include the labeled novelty data.