公开(公告)号：US20190278880A1

公开(公告)日：2019-09-12

申请号：US16295004

申请日：2019-03-07

Applicant: ExxonMobil Research and Engineering Company

Inventor： Ning Ma ,  Niranjan A. Subrahmanya ,  Wei D. Liu ,  Sumathy Raman

IPC: G06F17/50 ,  G06N3/08 ,  G06N20/00

Abstract: This disclosure generally relates to a methodology of effectively designing and/or discovering new materials based on microstructure, and more particularly, to designing and/or discovering new materials by combining material fundamentals and experimental data. The methodology disclosed herein provides cost-effective and time-effective solutions for material design that combine the benefits of both of the two major computational material design approaches: physics-based and data-driven computer models.

公开(公告)号：US10915073B2

公开(公告)日：2021-02-09

申请号：US16218650

申请日：2018-12-13

Applicant: ExxonMobil Research and Engineering Company

Inventor： Thomas A. Badgwell ,  Kuang-Hung Liu ,  Niranjan A. Subrahmanya ,  Wei D. Liu ,  Michael H. Kovalski

IPC: G05B11/42 ,  G05B11/06 ,  G06N3/04 ,  G06F17/13 ,  G06N3/08 ,  G05B11/01 ,  G06N3/00 ,  G06N7/00

Abstract: Systems and methods are provided for using a Deep Reinforcement Learning (DRL) agent to provide adaptive tuning of process controllers, such as Proportional-Integral-Derivative (PID) controllers. The agent can monitor process controller performance, and if unsatisfactory, can attempt to improve it by making incremental changes to the tuning parameters for the process controller. The effect of a tuning change can then be observed by the agent and used to update the agent's process controller tuning policy. It has been unexpectedly discovered that providing adaptive tuning based on incremental changes in tuning parameters, as opposed to making changes independent of current values of the tuning parameters, can provide enhanced or improved control over a controlled variable of a process.

公开(公告)号：US20190187631A1

公开(公告)日：2019-06-20

申请号：US16218650

申请日：2018-12-13

Applicant: ExxonMobil Research and Engineering Company

Inventor： Thomas A. Badgwell ,  Kuang-Hung Liu ,  Niranjan A. Subrahmanya ,  Wei D. Liu ,  Michael H. Kovalski

IPC: G05B11/42 ,  G05B11/06 ,  G05B11/01 ,  G06F17/13 ,  G06N3/08 ,  G06N3/04

CPC classification number: G05B11/42 ,  G05B11/011 ,  G05B11/06 ,  G06F17/13 ,  G06N3/04 ,  G06N3/08

Abstract: Systems and methods are provided for using a Deep Reinforcement Learning (DRL) agent to provide adaptive tuning of process controllers, such as Proportional-Integral-Derivative (PID) controllers. The agent can monitor process controller performance, and if unsatisfactory, can attempt to improve it by making incremental changes to the tuning parameters for the process controller. The effect of a tuning change can then be observed by the agent and used to update the agent's process controller tuning policy. It has been unexpectedly discovered that providing adaptive tuning based on incremental changes in tuning parameters, as opposed to making changes independent of current values of the tuning parameters, can provide enhanced or improved control over a controlled variable of a process.