公开(公告)号：WO2022132907A1

公开(公告)日：2022-06-23

申请号：PCT/US2021/063528

申请日：2021-12-15

Applicant: UNIVERSITY OF CINCINNATI ,  MAZAK CORPORATION

Inventor： AZAMFAR, Moslem ,  PANDHARE, Vibhor ,  MILLER, Marcella ,  LI, Fei ,  LI, Pin ,  SINGH, Jaskaran ,  DAVARI, Hossein ,  LEE, Jay ,  SANDERS, Joseph, Frank ,  YAMAGUCHI, Keita

IPC: G05B23/02

Abstract: Systems, methods, and computer program products for monitoring a health condition of a tool (34). Operational data is collected from a machine (14) while the machine (14) is operating in a predetermined manner with the tool (34) in each of at least two known health conditions. A plurality of features (138, 140, 142) is extracted from the operational data, a training dataset is generated from the extracted features (138, 140, 142), and an analytic model (54) is trained using the training dataset. The analytic model (54) can then be used to determine the health condition of the tool (34) by providing features (138, 140, 142) extracted from operational data received from one or more field machines (14) to the analytic model (54). The analytic model (54) may then determine a health condition of the tool (34) in the field machine (14) based on like features (138, 140, 142) extracted from the operational data from the one or more field machines (14).

公开(公告)号：WO2022132898A8

公开(公告)日：2022-06-23

申请号：PCT/US2021/063518

申请日：2021-12-15

Applicant: UNIVERSITY OF CINCINNATI ,  MAZAK CORPORATION

Inventor： AZAMFAR, Moslem ,  PANDHARE, Vibhor ,  MILLER, Marcella ,  Ll, Fei ,  Ll, Pin ,  SINGH, Jaskaran ,  DAVARI, Hossein ,  LEE, Jay ,  SANDERS, Joseph, Frank, Jr. ,  YAMAGUCHI, Keita

IPC: G05B23/02 ,  G05B19/4184 ,  G05B2219/31288 ,  G05B2219/32074 ,  G05B2219/37252 ,  G05B23/0235 ,  G05B23/0254 ,  G05B23/0283 ,  G05B23/0286

Abstract: Systems, methods, and computer program products for remaining useful life prediction. Operational data is collected from a test machine (14) until a component fails, and a training dataset generated from the operational data. The training dataset is used to define and validate a prediction model (54). Operational data received from one or more field machines (14) is provided to the prediction model (54). The prediction model (54) then predicts the remaining useful life of the component of the field machine (14). To reduce the time-to-failure of the component in the test machine (14), the component may be repeatedly subjected to an accelerated wear cycle (88). The prediction model (54) may be defined by extracting features from the training dataset. Like features may be extracted from the field dataset and provided to the prediction model (54) as part of the prediction process (100). The operational data received from the field machines (14) may be used to generate an updated prediction model (54).

公开(公告)号：WO2022132898A1

公开(公告)日：2022-06-23

申请号：PCT/US2021/063518

申请日：2021-12-15

Applicant: UNIVERSITY OF CINCINNATI ,  MAZAK CORPORATION

Inventor： AZAMFAR, Moslem ,  PANDHARE, Vibhor ,  MILLER, Marcella ,  LL, Fei ,  LL, Pin ,  SINGH, Jaskaran ,  DAVARI, Hossein ,  LEE, Jay ,  SANDERS, Joseph, Frank, Jr. ,  YAMAGUCHI, Keita

IPC: G05B23/02

Abstract: Systems, methods, and computer program products for remaining useful life prediction. Operational data is collected from a test machine (14) until a component fails, and a training dataset generated from the operational data. The training dataset is used to define and validate a prediction model (54). Operational data received from one or more field machines (14) is provided to the prediction model (54). The prediction model (54) then predicts the remaining useful life of the component of the field machine (14). To reduce the time-to-failure of the component in the test machine (14), the component may be repeatedly subjected to an accelerated wear cycle (88). The prediction model (54) may be defined by extracting features from the training dataset. Like features may be extracted from the field dataset and provided to the prediction model (54) as part of the prediction process (100). The operational data received from the field machines (14) may be used to generate an updated prediction model (54).