SYSTEM AND METHOD FOR FLOW RATE DATA DETERMINATION
A method includes obtaining raw multiphase flow rate data from a first set of sensors disposed on a pipeline of a well and obtaining auxiliary data from a second set of sensors disposed on the pipeline. The method further includes preprocessing the raw multiphase flow rate data to form a preprocessed multiphase flow rate dataset (“preprocessed dataset”), and determining, with a first model processing the preprocessed dataset, a first cleansed flow rate dataset. The method further includes determining, with a second model processing the preprocessed dataset and the auxiliary data, a second cleansed flow rate dataset. The method further includes determining high quality flow rate data with a third model processing the preprocessed dataset, the first cleansed flow rate dataset, and the second cleansed flow rate dataset. The method further includes transmitting the high quality flow rate data to a control system of the well.
1 . A method, comprising:
obtaining raw multiphase flow rate data from a first set of sensors disposed on a pipeline of a well;
obtaining auxiliary data from a second set of sensors disposed on the pipeline;
preprocessing the raw multiphase flow rate data to form a preprocessed multiphase flow rate dataset;
determining, with a first model processing the preprocessed multiphase flow rate dataset, a first cleansed flow rate dataset;
determining, with a second model processing the preprocessed multiphase flow rate dataset and the auxiliary data, a second cleansed flow rate dataset;
determining, with a third model processing the preprocessed multiphase flow rate dataset, the first cleansed flow rate dataset, and the second cleansed flow rate dataset, high quality flow rate data; and
transmitting the high quality flow rate data to, at least, a control system of the well, wherein operation of the well is based on the high quality flow rate data.
2 . The method of claim 1 , further comprising:
training, using a supervised learning process with a plurality of paired inputs and targets, a virtual flow meter (VFM) model, wherein a paired input and target consists of an input data point comprised by the auxiliary data and an associated high quality flow rate datapoint comprised by the high quality flow rate data.
3 . The method of claim 2 , further comprising:
determining, with the trained VFM model, predicted flow rate data based on newly obtained auxiliary data;
determining whether there is a malfunction in the first set of sensors based on the predicted flow rate data; and
using the predicted flow rate data instead of newly obtained raw multiphase flow rate data in response to the determination that the malfunction is the first set of sensors.
4 . The method of claim 2 , further comprising:
determining, with the trained VFM model, predicted flow rate data based on newly obtained auxiliary data; and
adjusting, one or more devices disposed on the pipeline based on the predicted flow rate data so as to optimize production of the well.
5 . The method of claim 1 , wherein operation of the well is controlled by adjusting one or more devices disposed on the pipeline.
6 . The method of claim 1 ,
wherein the auxiliary data comprises one of wellhead pressure, upstream wellhead temperature, downstream wellhead pressure, Venturi differential pressure, choke valve position, electrical submersible pump (ESP) frequency, and ESP motor current.
7 . The method of claim 1 , wherein at least one of the first model, the second model and the third model are machine-learned models.
8 . The method of claim 1 , wherein the first model is an auto regressive integrated moving average (ARIMA) model.
9 . The method of claim 1 , wherein the second model is a physics model, a machine-learned model, or a hybrid of a physics model and a machine-learned model.
10 . The method of claim 1 wherein the third model is a Gaussian mixture model.
11 . A system comprising:
a first set of sensors disposed on a pipeline of a well;
a second set of sensors disposed on the pipeline;
a set of models, comprising a first model, a second model and a third model; and
a computer configured to:
obtain raw multiphase flow rate data from a first set of sensors disposed on a pipeline of a well;
obtain auxiliary data from a second set of sensors disposed on the pipeline;
preprocess the raw multiphase flow rate data to form a preprocessed multiphase flow rate dataset;
determine, with a first model processing the preprocessed multiphase flow rate dataset, a first cleansed flow rate dataset;
determine, with a second model processing the preprocessed multiphase flow rate dataset and the auxiliary data, a second cleansed flow rate dataset;
determine, with a third model processing the preprocessed multiphase flow rate dataset, the first cleansed flow rate dataset, and the second cleansed flow rate dataset, high quality flow rate data; and
transmit the high quality flow rate data to, at least, a control system of the well, wherein operation of the well is based on the high quality flow rate data.
12 . The system of claim 11 , the computer further configured to:
train, using a supervised learning process with a plurality of paired inputs and targets, a virtual flow meter (VFM) model, wherein a paired input and target consists of an input data point comprised by the auxiliary data and an associated high quality flow rate datapoint comprised by the high quality flow rate data.
13 . The system of claim 12 , the computer further configured to:
determine, with the trained VFM model, predicted flow rate data based on newly obtained auxiliary data;
determine whether there is a malfunction in the first set of sensors based on the predicted flow rate data; and
use the predicted flow rate data instead of newly obtained raw multiphase flow rate data in response to the determination that the malfunction is the first set of sensors.
14 . The system of claim 12 , the computer further configured to:
determine with the trained VFM model, predicted flow rate data based on newly obtained auxiliary data; and
adjust, one or more devices disposed on the pipeline based on the predicted flow rate data so as to optimize production of the well.
15 . The system of claim 11 , wherein operation of the well is controlled by adjusting one or more devices disposed on the pipeline.
16 . The system of claim 11 ,
wherein the auxiliary data comprises one of wellhead pressure, upstream wellhead temperature, downstream wellhead pressure, Venturi differential pressure, choke valve position, electrical submersible pump (ESP) frequency, and ESP motor current.
17 . The system of claim 11 , wherein the first model is an auto regressive integrated moving average (ARIMA) model.
18 . The system of claim 11 , wherein the second model is a physics model, a machine-learned model, or a hybrid of a physics model and a machine-learned model.
19 . The system of claim 11 wherein the third model is a Gaussian mixture model.
20 . A non-transitory machine-readable medium comprising a plurality of machine-readable instructions executed by one or more processors, the plurality of machine-readable instructions causing the one or more processors to perform a method comprising:
obtaining raw multiphase flow rate data from a first set of sensors disposed on a pipeline of a well;
obtaining auxiliary data from a second set of sensors disposed on the pipeline;
preprocessing the raw multiphase flow rate data to form a preprocessed multiphase flow rate dataset;
determining, with a first model processing the preprocessed multiphase flow rate dataset, a first cleansed flow rate dataset;
determining, with a second model processing the preprocessed multiphase flow rate dataset and the auxiliary data, a second cleansed flow rate dataset;
determining, with a third model processing the preprocessed multiphase flow rate dataset, the first cleansed flow rate dataset, and the second cleansed flow rate dataset, high quality inferred flow rate data; and
transmitting the high quality flow rate data to, at least, a control system of the well, wherein operation of the well is based on the high quality flow rate data.