公开(公告)号：US20190205751A1

公开(公告)日：2019-07-04

申请号：US16235355

申请日：2018-12-28

Applicant: University of Southern California ,  Chevron U.S.A. Inc.

Inventor： CHUNGMING CHEUNG ,  PALASH GOYAL ,  ARASH SABER TEHRANI ,  VIKTOR K. PRASANNA ,  LISA ANN BRENSKELLE

IPC: G06N3/08 ,  G06N20/10 ,  G06N5/04 ,  G06F17/18 ,  E21B47/00

CPC classification number: G06N3/08 ,  E21B47/00 ,  E21B2041/0028 ,  G06F17/18 ,  G06N3/084 ,  G06N5/046 ,  G06N20/10

Abstract: A computer-implemented method for prioritizing candidate objects on which to perform a physical process includes receiving a time series history of measurements from each of a plurality of candidate objects at a data processing framework. The method further includes reducing dimensionality of the time series history of measurements with a convolutional autoencoder to obtain latent features for each of the plurality of candidate objects. The method also includes applying a kernel regression model to the latent features to generate a predicted value of physical output for performing the physical process on each of the plurality of candidate objects. The method additionally includes generating a prioritization of the candidate objects based on the values of physical output. The method involves selecting fewer than all of the plurality of candidate objects on which to perform the physical process. The selected candidate objects are based on the prioritization.

公开(公告)号：US20190205360A1

公开(公告)日：2019-07-04

申请号：US16235387

申请日：2018-12-28

Applicant: University of Southern California ,  Chevron U.S.A. Inc.

Inventor： CHUNGMING CHEUNG ,  PALASH GOYAL ,  ARASH SABER TEHRANI ,  VIKTOR K. PRASANNA ,  LISA ANN BRENSKELLE

IPC: G06F17/18 ,  G06N20/10 ,  G06N3/08 ,  E21B47/00

CPC classification number: G06N3/08 ,  E21B47/00 ,  E21B2041/0028 ,  G06F17/18 ,  G06N3/084 ,  G06N5/046 ,  G06N20/10

Abstract: A computer-implemented method for prioritizing candidate objects on which to perform a physical process includes receiving a time series history of measurements from each of a plurality of candidate objects at a data processing framework. The method further includes reducing dimensionality of the time series history of measurements with a convolutional autoencoder to obtain latent features for each of the plurality of candidate objects. The method also includes applying a kernel regression model to the latent features to generate a predicted value of physical output for performing the physical process on each of the plurality of candidate objects. The method additionally includes generating a prioritization of the candidate objects based on the values of physical output. The method involves selecting fewer than all of the plurality of candidate objects on which to perform the physical process. The selected candidate objects are based on the prioritization.