Method and system for multiphase flow meter using updated flow model based on simulated data
A method may include obtaining, from various sensors, acquired sensor data regarding various multiphase flows in a multiphase flow meter that are sampled at a predetermined sampling frequency. The acquired sensor data may describe various transient signals that correspond to various gas droplets. The method may further include generating, based on the acquired sensor data, a flow model for the multiphase flow meter. The method may further include updating the flow model to produce a first updated flow model using simulated flow data. The method may further include updating the first updated flow model to produce a second updated flow model using simulated sensor data. The second updated flow model may be used to determine one or more flow rates within a multiphase flow.
1. A method, comprising:
obtaining, by a computer processor and from a plurality of sensors, acquired sensor data regarding one or more multiphase flows in a multiphase flow meter that are sampled at a predetermined sampling frequency, wherein the acquired sensor data describes a plurality of transient signals that correspond to a plurality of gas droplets;
generating, by the computer processor and based on the acquired sensor data, a flow model for the multiphase flow meter;
updating, by the computer processor, the flow model to produce a first updated flow model using simulated flow data; and
updating, by the computer processor, the first updated flow model to produce a second updated flow model using simulated sensor data,
wherein the second updated flow model is used to determine one or more flow rates within a multiphase flow, and
wherein the predetermined sampling frequency corresponds to a frequency value greater than a ratio of a predetermined flow velocity to a size of a sensing electrode for an electromagnetic measurement of the one or more multiphase flows.
2. The method of claim 1 , further comprising:
generating, using an artificial neural network and flow condition data, the simulated flow data; and
validating, using tomographic imaging data of the multiphase flow meter, the simulated flow data,
wherein the simulated flow data is used to update the flow model in response to validating the simulated flow data.
3. The method of claim 1 , further comprising:
generating, using an artificial neural network, the simulated sensor data; and
validating, using the acquired sensor data, the simulated sensor data,
wherein the simulated sensor data is used to update the flow model in response to validating the simulated sensor data.
4. The method of claim 1 ,
wherein the simulated flow data and the simulated sensor data are generated using a temporal convolution network (TCN).
5. The method of claim 1 ,
wherein the simulated sensor data corresponds to an electromagnetic sensor response in the multiphase flow meter, and
wherein the plurality of sensors comprise one or more impedance sensors.
6. The method of claim 1 ,
wherein the simulated sensor data corresponds to an acoustic response in the multiphase flow meter, and
wherein the plurality of sensors comprise one or more acoustic sensors.
7. The method of claim 1 , further comprising:
determining, using a gamma ray source and a gamma ray detector among the plurality of sensors, gas-oil ratio (GOR) data regarding the one or more multiphase flows,
wherein the GOR data is used to generate the flow model.
8. The method of claim 1 ,
wherein the plurality of sensors comprise at least one sensing electrode, and
wherein the predetermined sampling frequency corresponds to a range from 100 Hz to 1000 Hz.
9. The method of claim 1 ,
wherein the second updated flow model describes a plurality of flow regimes and a plurality of phase distributions, and
wherein the second updated flow model is used by a flow controller in the multiphase flow meter to determine a fraction of gas in the multiphase flow.
10. The method of claim 1 , further comprising:
determining, using the multiphase flow meter and the second updated flow model, a fraction of oil, a fraction of gas, and a fraction of water in a production stream at a wellhead.
11. An apparatus, comprising:
a flow tube configured to receive a multiphase flow;
a plurality of sensors coupled to the flow tube;
a flow controller coupled to the plurality of sensors and the flow tube, the flow controller comprising:
a processor,
driver circuitry for operating the plurality of sensors, and
a flow model, and
wherein the flow model is based on acquired sensor data, simulated flow data, and simulated sensor data,
wherein the flow controller uses the flow model to determine one or more fractions of the multiphase flow,
wherein the plurality of sensors comprise at least one sensing electrode operating at a predetermined sampling frequency, and wherein the predetermined sampling frequency corresponds to a frequency value greater than a ratio of a predetermined flow velocity to a size of the at least one sensing electrode for an electromagnetic measurement of one or more multiphase flows.
12. The apparatus of claim 11 ,
wherein the plurality of sensors comprise an absolute pressure sensor, a temperature sensor, a differential pressure sensor, a gamma ray source, and a gamma ray detector.
13. The apparatus of claim 11 ,
wherein the simulated flow data is generated using an artificial neural network and a plurality of flow scenarios,
wherein the simulated flow data is validated using tomographic imaging data of one or more multiphase flows in the flow tube, and
wherein the simulated flow data is used to update the flow model in response to validating the simulated flow data.
14. The apparatus of claim 11 ,
wherein the plurality of sensors comprise one or more impedance sensors, and
wherein the simulated sensor data corresponds to an electromagnetic sensor response.
15. The apparatus of claim 11 ,
wherein the plurality of sensors comprise one or more acoustic sensors, and
wherein the simulated sensor data corresponds to an acoustic response.
16. The apparatus of claim 11 ,
wherein the plurality of sensors comprise at least one sensing electrode operating at a predetermined sampling frequency, and
wherein the predetermined sampling frequency corresponds to a range from 100 Hz to 1000 Hz.
17. The apparatus of claim 11 ,
wherein the flow model describes a plurality of flow regimes and a plurality of phase distributions, and
wherein the plurality of flow regimes comprises a bubble regime regarding a gas phase of the multiphase flow.
18. A system, comprising:
a wellhead coupled to a wellbore, the wellhead configured to obtain a production stream from a subterranean formation;
a multiphase flow meter coupled to the wellhead, the multiphase flow meter comprising:
a flow tube,
a plurality of sensors coupled to the flow tube; and
a flow controller coupled to the plurality of sensors and the flow tube, the flow controller comprising a flow model; and
a well control system coupled to the multiphase flow meter,
wherein the flow model is based on acquired sensor data, simulated flow data, and simulated sensor data,
wherein the flow controller uses the flow model to determine a first fraction of oil in the production stream, a second fraction of water in the production stream, and a third fraction of water in the production stream,
wherein the plurality of sensors comprise at least one sensing electrode operating at a predetermined sampling frequency, and
wherein the predetermined sampling frequency corresponds to a frequency value greater than a ratio of a predetermined flow velocity to a size of the at least one sensing electrode for an electromagnetic measurement of one or more multiphase flows.