公开(公告)号：US11899527B2

公开(公告)日：2024-02-13

申请号：US17539011

申请日：2021-11-30

Applicant: Caterpillar Inc.

Inventor： David J. Lin ,  Tyler P. Jewell ,  Daniel J. Organ ,  Vivek Sundararaj ,  Vijay K. Yalamanchili ,  Chanyoung Park ,  William Kent Rutan ,  Kaimei Sun

IPC: G06F11/07

CPC classification number: G06F11/079 ,  G06F11/0736

Abstract: A method for identifying a cause of a machine operating anomaly including creating a reduced order model (ROMs) for a digital twin model of a selected machine type and feeding current data from a deployed machine into the ROM. The method can include comparing a current output from the selected ROM with a measured output from the current data and determining that an operating anomaly exists when the difference between the current output and the measured output exceeds a selected anomaly threshold. The cause of the operating anomaly can be identified by feeding the current data into a plurality of fault models, wherein each fault model includes a particular component failure, comparing a fault model output from each of the plurality of fault models with the measured output from the current data, selecting the fault model with the fault model output most closely matching the measured output, and displaying the identified component failure associated with the selected fault model as the cause of the operating anomaly.

公开(公告)号：US20230168961A1

公开(公告)日：2023-06-01

申请号：US17539011

申请日：2021-11-30

Applicant: Caterpillar Inc.

Inventor： David J. Lin ,  Tyler P. Jewell ,  Daniel J. Organ ,  Vivek Sundararaj ,  Vijay K. Yalamanchili ,  Chanyoung Park ,  William Kent Rutan ,  Kaimei Sun

IPC: G06F11/07

CPC classification number: G06F11/079 ,  G06F11/0736

Abstract: A method for identifying a cause of a machine operating anomaly including creating a reduced order model (ROMs) for a digital twin model of a selected machine type and feeding current data from a deployed machine into the ROM. The method can include comparing a current output from the selected ROM with a measured output from the current data and determining that an operating anomaly exists when the difference between the current output and the measured output exceeds a selected anomaly threshold. The cause of the operating anomaly can be identified by feeding the current data into a plurality of fault models, wherein each fault model includes a particular component failure, comparing a fault model output from each of the plurality of fault models with the measured output from the current data, selecting the fault model with the fault model output most closely matching the measured output, and displaying the identified component failure associated with the selected fault model as the cause of the operating anomaly.

公开(公告)号：US11640164B2

公开(公告)日：2023-05-02

申请号：US17219710

申请日：2021-03-31

Applicant: Caterpillar Inc.

Inventor： Harsheel R. Shah ,  Chanyoung Park

IPC: G05B23/02

Abstract: The present disclosure is directed to systems and methods for predicting risk of machine components not achieving their agreed life based on historical data. In some implementations, the predicting component risk system can obtain historical component specific time series data and component life data that correspond to a specific component of a type of machine. Using the component specific time series data and component life data, the predicting component risk system can train a time-series model. After training the model, the predicting component risk system can obtain current component specific data that includes information on the current condition and usage of the component. Using the trained time-series model, the predicting component risk system can determine a risk score for the current component specific data and notify maintenance entities of the risk. The risk score can represent the risk that the specific component does not achieve agreed life.

公开(公告)号：US20220317677A1

公开(公告)日：2022-10-06

申请号：US17219710

申请日：2021-03-31

Applicant: Caterpillar Inc.

Inventor： Harsheel R. Shah ,  Chanyoung Park

IPC: G05B23/02

Abstract: The present disclosure is directed to systems and methods for predicting risk of machine components not achieving their agreed life based on historical data. In some implementations, the predicting component risk system can obtain historical component specific time series data and component life data that correspond to a specific component of a type of machine. Using the component specific time series data and component life data, the predicting component risk system can train a time-series model. After training the model, the predicting component risk system can obtain current component specific data that includes information on the current condition and usage of the component. Using the trained time-series model, the predicting component risk system can determine a risk score for the current component specific data and notify maintenance entities of the risk. The risk score can represent the risk that the specific component does not achieve agreed life.