Dynamic real time gross rate monitoring through subsurface and surface data
Continuous gross rate of each of a plurality of wells is estimated. Information provided by sensors configured with each of a plurality of electrical submersible pumps is received. Information associated with a respective model of each of the plurality of electrical submersible pumps is accessed. Utilizing at least one of artificial intelligence and machine learning, the information provided by sensors and the information associated with the respective model of each of the plurality of electrical submersible pumps is processed to estimate a first gross rate of each of the plurality of wells. A second gross rate of each of the plurality of wells is estimated via a pipeline simulation that applies a physics-based model. A continuous gross rate for each of the plurality of wells is estimated as a function the first gross rate and the second gross rate.
1. A computer-implemented method for estimating continuous gross rate of each of a plurality of wells that do not have available rate testing, the method comprising:
training, by at least one computing device, a model to predict a well's continuous gross rate, wherein the training includes:
processing historical well information that is respectively associated with at least one pump associated with a well, wherein the historical well information represents well-head upstream pressure, pump upstream pressure, pump downstream pressure, pump motor speed, pump horsepower, sum of stages, and depth of pump installation;
generating, as a function of the processed historical well information, a continuous gross rate prediction for the well;
testing the continuous gross rate prediction for the well using historical well output information representing continuous gross rate of the well;
repeating the steps of processing the historical well information, generating the continuous gross rate prediction for the well, and testing the continuous gross rate prediction for the well until the continuous gross rate prediction for the well consistently correlates with the historical well information; and
providing, after the continuous gross rate prediction for the well consistently correlates with the historical well information, the trained model;
receiving, by the at least one computing device, information including measurements obtained from an active well that does not have available rate testing and is associated with each of a plurality of electrical submersible pumps, wherein the information includes:
respective pump model; respective wellhead upstream pressure;
respective electrical submersible pump upstream pressure; respective electrical submersible pump downstream pressure; respective electrical submersible pump motor speed; respective electrical submersible pump horsepower; respective sum of stages in a respective pump; and respective depth of electrical submersible pump installation;
processing, by the at least one computing device using the trained model, the received measurements associated with each of the at least one electrical submersible pump;
generating, by the at least one computing device as a function of processing the received measurements, a continuous gross rate prediction of the active well;
correlating, by the at least one computing device, at least one gross rate estimated by utilizing at least one of artificial intelligence and machine learning using information representing flowrate of at least one well that is physically measured; and
adjusting, by the at least one computing device, the at least one of the artificial intelligence and machine learning as a function of the correlating.
2. The method of claim 1 , further comprising applying, by the at least one computing device, a quantic inflow performance equation; and
substituting, by the at least one computing device, a result of the quantic inflow performance equation for a difference of measured intake pressure and measured discharge pressure of at least one of the electrical submersible pumps.
3. The method of claim 2 , wherein the quantic inflow performance equation applies a respective frequency of each respective electrical submersible pump head.
4. The method of claim 3 , further comprising:
generating, by the at least one computing device, a pump performance curve for each of the plurality of electrical submersible pumps; and
applying, by the at least one computing device, at least some of the information provided by sensors and the information associated with the respective model of each of the plurality of electrical submersible pumps to the pump performance curve to estimate the second gross rate of each of the plurality of wells.
5. The method of claim 1 , wherein the information processing by utilizing at least one of artificial intelligence and machine learning and provided by the sensors configured with each of the plurality of electrical submersible pumps includes well-head upstream pressure, electrical submersible pump upstream pressure, electrical submersible pump downstream pressure, electrical submersible pump motor speed, electrical submersible pump horsepower, sum of stages in the pump, and depth of electrical submersible pump installation.
6. The method of claim 1 , wherein at least some of the information that is associated with a respective model of each of the plurality of electrical submersible pumps includes a number of stages for each of the plurality of electrical submersible pumps, and further comprising:
determining, by the least one computing device for each of the plurality of electrical submersible pumps, a head-per-stage value.
7. The method of claim 1 , further comprising:
receiving, by the at least one computing device, information measured by a multiphase flow meter, wherein the information represents a flowrate of at least one of the electrical submersible pumps; and
determining, by the at least one computing device comparing the flowrate measured by the multiphase flow meter and at least information associated with the estimated continuous gross rate, a malfunction of the multiphase flow meter.
8. The method of claim 1 , wherein the information provided by the sensors includes well-head upstream pressure, electrical submersible pump upstream pressure, electrical submersible pump downstream pressure, electrical submersible pump motor speed, electrical submersible pump horsepower, sum of stages in a pump, and depth of an electrical submersible pump installation.
9. The method of claim 1 , wherein the pipeline simulation is provided as a function of at least one of intake pressure, discharge pressure, electrical submersible pump horsepower, electrical submersible pump motor speed, and a sum of stages in an electrical submersible pump.
10. A computer-implemented system for estimating continuous gross rate of each of a plurality of wells that do not have available rate testing, the system comprising:
at least one computing device, wherein the at least one computing device is configured by executing instructions for:
training a model to predict a well's continuous gross rate, wherein the training includes:
processing historical well information that is respectively associated with at least one pump associated with a well, wherein the historical well information represents well-head upstream pressure, pump upstream pressure, pump downstream pressure, pump motor speed, pump horsepower, sum of stages, and depth of pump installation;
generating, as a function of the processed historical well information, a continuous gross rate prediction for the well;
testing the continuous gross rate prediction for the well using historical well output information representing continuous gross rate of the well;
repeating the steps of processing the historical well information, generating the continuous gross rate prediction for the well, and testing the continuous gross rate prediction for the well until the continuous gross rate prediction for the well consistently correlates with the historical well information; and
providing, after the continuous gross rate prediction for the well consistently correlates with the historical well information, the trained model;
receiving information including measurements obtained from an active well that does not have available rate testing and is associated with each of a plurality of electrical submersible pumps, wherein the information includes:
respective pump model; respective wellhead upstream pressure; respective electrical submersible pump upstream pressure; respective electrical submersible pump downstream pressure; respective electrical submersible pump motor speed; respective electrical submersible pump horsepower; respective sum of stages in a respective pump; and
respective depth of electrical submersible pump installation;
processing, using the trained model, the received measurements associated with each of the at least one electrical submersible pump;
generating, as a function of processing the received measurements, a continuous gross rate prediction of the active well-;
correlating at least one gross rate estimated by utilizing at least one of artificial intelligence and machine learning using information representing flowrate of at least one well that is physically measured; and
adjusting the at least one of the artificial intelligence and machine learning as a function of the correlating.
11. The system of claim 10 , wherein the at least one computing device is configured by executing instructions for:
applying, by the at least one computing device, a quantic inflow performance equation; and
substituting, by the at least one computing device, a result of the quantic inflow performance equation for a difference of measured intake pressure and measured discharge pressure of at least one of the electrical submersible pumps.
12. The system of claim 11 , wherein the quantic inflow performance equation applies a respective frequency of each respective electrical submersible pump head.
13. The system of claim 11 , wherein the at least one computing device is configured by executing instructions for:
generating a pump performance curve for each of the plurality of electrical submersible pumps; and
applying at least some of the information provided by sensors and the information associated with the respective model of each of the plurality of electrical submersible pumps to the pump performance curve to estimate the second gross rate of each of the plurality of wells.
14. The system of claim 10 , wherein the information processing by utilizing at least one of artificial intelligence and machine learning and provided by the sensors configured with each of the plurality of electrical submersible pumps includes well-head upstream pressure, electrical submersible pump upstream pressure, electrical submersible pump downstream pressure, electrical submersible pump motor speed, electrical submersible pump horsepower, sum of stages in the pump, and depth of electrical submersible pump installation.
15. The system of claim 10 , wherein at least some of the information that is associated with a respective model of each of the plurality of electrical submersible pumps includes a number of stages for each of the plurality of electrical submersible pumps, and further wherein the at least one computing device is configured by executing instructions for:
determining, for each of the plurality of electrical submersible pumps, a head-per-stage value.
16. The system of claim 10 , wherein the at least one computing device is configured by executing instructions for:
receiving information measured by a multiphase flow meter, wherein the information represents a flowrate of at least one of the electrical submersible pumps; and
determining, by comparing the flowrate measured by the multiphase flow meter and at least information associated with the estimated continuous gross rate, a malfunction of the multiphase flow meter.
17. The system of claim 10 , wherein the information provided by the sensors includes well-head upstream pressure, electrical submersible pump upstream pressure, electrical submersible pump downstream pressure, electrical submersible pump motor speed, electrical submersible pump horsepower, sum of stages in a pump, and depth of an electrical submersible pump installation.
18. The system of claim 10 , wherein the pipeline simulation is provided as a function of at least one of intake pressure, discharge pressure, electrical submersible pump horsepower, electrical submersible pump motor speed, and a sum of stages in an electrical submersible pump.