Multi-objective optimization on modeling and optimizing scaling and corrosion in a wellbore
System for optimizing operation of an oil and gas well employs multi-objective Bayesian optimization of wellbore parameters to minimize scaling and corrosion. The system may contain instrumentation for measuring temperature, pressure, at least one production parameter and at least one ion concentration of the fluid in the wellbore. The system may also have a processor for performing a calculation procedure to determine an anticipated corrosion rate (“Vbase”) and a scaling index (“Is”) reflecting a tendency of scale to form in the wellbore based on the measurements provided by the instrumentation, where Vbase and Is are calculated along the length of the wellbore. Based on a selected set of optimization points taken from the calculations of Vbase and Is, the system may control the alkalinity and flow rate of the fluid based on the multi-objective optimization to simultaneously optimize scaling and corrosion.
1. A method for optimizing scaling and corrosion in an oil field tubular, comprising:
obtaining a set of input parameters related to a fluid flowing in the oil field tubular;
performing a base calculation procedure to determine a corrosion rate and a scaling index reflecting a tendency of scale to form in the oil field tubular based on the set of input parameters, wherein the base calculation procedure yields a range of values for the corrosion rate and the scaling index along the oil field tubular;
selecting optimization points from the ranges of the corrosion rate and the scaling index obtained from the base calculation procedure, wherein the optimization points are selected at particular depths along the oil field tubular, and wherein at least one of the selected optimization points is selected at a depth that has a maximum value for the corrosion rate or the scaling index;
performing a multi-objective optimization for the selected optimization points of the corrosion rate and the scaling index; and
controlling an alkalinity and flow rate of the fluid based on the multi-objective optimization.
2. The method of claim 1 , wherein the step of obtaining the set of input parameters comprises obtaining a temperature and pressure of the fluid in the oil field tubular.
3. The method of claim 1 , wherein the step of obtaining the set of input parameters comprises obtaining an ion concentration present in the fluid.
4. The method of claim 1 , wherein the oil field tubular comprises one or more of a production tubing in a wellbore and a section of pipe in a pipeline.
5. The method of claim 4 , wherein the step of obtaining the set of input parameters comprises:
obtaining a temperature and pressure of the fluid in the oil field tubular;
obtaining a BWPD, BOPD, flow rate, API gravity, and production tubing inner diameter of the wellbore; and
obtaining ion concentrations of at least one of calcite, barium, strontium, iron, magnesium, weak organic acids, total alkalinity, sulfate, or chloride.
6. The method of claim 1 , wherein the step of performing the base calculation procedure comprises using an empirical model to determine the corrosion rate and the scaling index.
7. The method of claim 1 , wherein the step of performing the base calculation procedure comprises using machine learning to determine the corrosion rate and the scaling index.
8. The method of claim 7 , wherein the step of using machine learning comprises using a Deep Neural Network.
9. A system for optimizing scaling and corrosion in an oil field tubular, comprising:
a processor; and
a memory unit storing computer-readable instructions that, when executed by the processor, causes the system to,
obtain a set of input parameters related to fluid flowing in the oil field tubular;
perform a base calculation procedure to determine a corrosion rate and a scaling index reflecting a tendency of scale to form in the oil field tubular based on the set of input parameters, wherein the base calculation procedure yields a range of values for the corrosion rate and the scaling index along the oil field tubular;
select optimization points from the ranges of the corrosion rate and the scaling index obtained from the base calculation procedure, wherein the optimization points are selected at particular depths along the oil field tubular, and wherein at least one of the selected optimization points is selected at a depth that has a maximum value for the corrosion rate or the scaling index;
perform a multi-objective optimization for the selected optimization points of the corrosion rate and the scaling index; and
control an alkalinity and flow rate of the fluid based on the multi-objective optimization.
10. The system of claim 9 , wherein the set of input parameters comprises temperature and pressure of the fluid in the oil field tubular.
11. The system of claim 9 , wherein the set of input parameters comprises ion concentrations present in the fluid.
12. The system of claim 9 , wherein the oil field tubular comprises one or more of a production tubing in a wellbore and a section of pipe in a pipeline.
13. The system of claim 12 , wherein the computer-readable instructions cause the system to obtain the set of input parameters by:
obtaining a temperature and pressure of the fluid in the oil field tubular;
obtaining a BWPD, BOPD, flow rate, API gravity, and production tubing inner diameter of the wellbore; and
obtaining ion concentrations of at least one of calcite, barium, strontium, iron, magnesium, weak organic acids, total alkalinity, sulfate, or chloride.
14. The system of claim 9 , wherein the computer-readable instructions cause the system to perform the base calculation procedure using an empirical model to determine the corrosion rate and the scaling index.
15. The system of claim 9 , wherein the computer-readable instructions cause the system to perform the base calculation procedure using machine learning to determine the corrosion rate and the scaling index.
16. The system of claim 15 , wherein the computer-readable instructions cause the system to use machine learning by using a Deep Neural Network.
17. A system for operating an oil and gas well to minimize scaling and corrosion, comprising:
instrumentation located about a wellbore of the oil and gas well for measuring temperature, pressure, at least one production parameter and at least one ion concentration of a fluid in the wellbore; and
a processor for performing a base calculation procedure to determine a corrosion rate and a scaling index reflecting a tendency of scale to form in the wellbore based on the measurements provided by the instrumentation, wherein the corrosion rate and the scaling index are calculated along a length of the wellbore,
wherein, based on a selected set of optimization points taken from the calculations of the corrosion rate and the scaling index that are selected at particular depths along the wellbore, wherein at least one of the selected optimization points is selected at a depth that has a maximum value for the corrosion rate or the scaling index, the processor is adapted to perform a multi-objective optimization for the selected optimization points of the corrosion rate and the scaling index and control an alkalinity and flow rate of the fluid based on the multi-objective optimization.
18. The system of claim 17 , wherein the processor performs the base calculation procedure using a Deep Neural Network.
19. The system of claim 17 , wherein the processor performs the multi-objective optimization using Bayesian optimization.
20. The system of claim 19 , wherein the processor is adapted to control, based on the Bayesian optimization, one or more of:
temperature and pressure of the fluid in the wellbore;
a BWPD, BOPD, flow rate, API gravity, and production tubing inner diameter of the wellbore; and
ion concentrations of at least one of calcite, barium, strontium, iron, magnesium, weak organic acids, total alkalinity, sulfate, or chloride.