公开(公告)号：US20190093474A1

公开(公告)日：2019-03-28

申请号：US15712477

申请日：2017-09-22

Applicant: GENERAL ELECTRIC COMPANY

Inventor： Samhitha Palanganda Poonacha ,  Edward Randall Furlong ,  Anusha Rammohan ,  Aditya Bhakta ,  Abhirup Mondal ,  Vinod Veera Reddy

IPC: E21B47/10

Abstract: A method includes receiving field measurement data of a plurality of well-pumps disposed respectively in a plurality of wells. The field measurement data are representative of speed data and run-time data of the plurality of well-pumps. The method further includes receiving commingled-flow measurement data. The commingled-flow measurement data are representative of a combined fluid flow data of the plurality of wells. The method further includes determining, by an optimizer unit, well-flow data of the plurality of wells based on the commingled-flow measurement data, the field measurement data, and a plurality of conservation constraints generated by a constraint generator. The well-flow data are representative of fluid flow data from each of the plurality of wells. The method also includes controlling operation of at least one of the plurality of well-pumps based on the well-flow data to control fluid production from the plurality of wells.

公开(公告)号：US11334834B2

公开(公告)日：2022-05-17

申请号：US15601145

申请日：2017-05-22

Applicant: General Electric Company

Inventor： Subhankar Ghosh ,  Abhirup Mondal ,  Necip Doganaksoy ,  Hongyan Liu ,  Zhanpan Zhang ,  Robert August Kaucic ,  Jay Zhiqiang Cao

IPC: G06Q10/06 ,  G06F16/48 ,  H02J3/38 ,  F03D7/04

Abstract: The system and method described herein relate to production of power from the wind farm that incorporate tunable power production forecasts for optimal wind farm performance, where the wind farm power production is controlled at least in part by the power production forecasts. The system and method use a tunable power forecasting model to generate tunable coefficients based on asymmetric loss function applied on actual power production data, along with tuning factor(s) that tune forecast towards under forecasting or over forecasting. The power production forecasts are generated using the tunable coefficients 34 and power characteristic features that are derived from actual power production data. The power production forecasts are monitored for any degradation, and a control action to regenerate the coefficients or retune the model is undertaken if degradation is observed.