| CPC G05B 13/042 (2013.01) [E21B 44/00 (2013.01); E21B 47/07 (2020.05); E21B 47/10 (2013.01); G05B 13/0265 (2013.01); G06F 30/27 (2020.01); E21B 2200/20 (2020.05); E21B 2200/22 (2020.05)] | 15 Claims |
|
1. A method of managing a well system, comprising:
obtaining, by a digital twin manager and based on a predetermined monitoring criterion, well dynamics behavior data of the well system;
obtaining, by the digital twin manager, modeled well dynamics behavior data for the well system using a physics-based model, wherein the physics-based model includes a valve module that corresponds to and emulates a control mechanism of the well system;
decomposing, by the digital twin manager, each of the well dynamics behavior data and the modeled well dynamics behavior data into a plurality of frequency band components based on a plurality of predetermined frequency partitions;
training, by the digital twin manager, a physics constrained machine learning model using one or more machine learning algorithms based on the plurality of frequency band components of the decomposed well dynamics behavior data and the decomposed modeled well dynamics behavior data as input data;
obtaining, by the digital twin manager, new well dynamics behavior data of the well system;
using the physics constrained machine learning model and the physics-based model, by the digital twin manager, to generate and output predicted well dynamics behavior data based on the new well dynamics behavior data; and
transmitting, by the digital twin manager, a command to the well system that adjusts the control mechanism of the well system based on the predicted well dynamics behavior data,
wherein the predicted well dynamics behavior data are predicted in frequency band components corresponding to the plurality of predetermined frequency partitions,
wherein the plurality of predetermined frequency partitions increase in size from a smallest predetermined frequency partition to a largest predetermined frequency partition,
wherein a frequency range of the smallest predetermined frequency partition is entirely included in each of the plurality of predetermined frequency partitions, and
wherein the physics constrained machine learning model iteratively predicts the predicted frequency band components from the smallest predetermined frequency partition to the largest predetermined frequency partition that includes the frequency range of the smallest predetermined frequency partition.
|