Hydrocarbon well production optimization with fluid composition prediction

Abstract

Methods and systems for controlling hydrocarbon production in wells include operations for receiving, from sensors of wells, well data representing operation of the wells; retrieving an optimization model defined based on a plurality of operational parameters of the wells, the operational parameters specifying operational constraints for each of the wells; processing, by the optimization model, the well data and generating a solution set of operational states for each of the wells that optimizes hydrocarbon production at each of the wells; based on the processing, selecting, from the solution set, at least one solution that specifies an operational state for each of the wells, the operational state optimizing the hydrocarbon production for that well of the wells; and generating, for the wells, instructions for controlling well production; and sending, to the wells, the instructions.

What is claimed is: 
     
         1 . A method for controlling hydrocarbon production in one or more wells, the method comprising:
 receiving, from one or more sensors of one or more wells, well data representing operation of the one or more wells;   retrieving an optimization model defined based on a plurality of operational parameters of the one or more wells, the operational parameters specifying operational constraints for each of the one or more wells;   processing, by the optimization model, the well data and generating a solution set of operational states for each of the one or more wells that optimizes hydrocarbon production at each of the one or more wells;   based on the processing, selecting, from the solution set, at least one solution that specifies an operational state for each of the one or more wells, the operational state optimizing the hydrocarbon production for that well of the one or more wells;   generating, for the one or more wells, instructions for controlling well production; and   sending, to the one or more wells, the instructions.   
     
     
         2 . The method of  claim 1 , further comprising controlling, based on the instructions, well production at the one or more wells. 
     
     
         3 . The method of  claim 1 , wherein the optimization model is configured to maximize a molecular weight of a flash gas (MWF) for a well of the one or more wells or for a group of wells of the one or more wells. 
     
     
         4 . The method of  claim 1 , wherein the operational parameters comprise, for a given well of the one or more wells, a flowing bottom hole reservoir pressure, a bubble point pressure, and an initial production rate (TR). 
     
     
         5 . The method of  claim 1 , wherein the at least one solution includes a higher-ranking solution in the solution set, the higher-ranking solution being ranked higher than at least one lower-ranked solution in the solution set. 
     
     
         6 . The method of  claim 1 , wherein the well data comprises at least one of a flow rate in a wellbore of a well of the one or more wells, a wellbore pressure of the well of the one or more wells, a wellbore temperature of the well of the one or more wells, a fluid composition associated with the well of the one or more wells, and a well depth of the well of the one or more wells. 
     
     
         7 . The method of  claim 1 , wherein processing, by the optimization model, the well data comprises tracking one or more Pareto-optimal solutions of the solution set; and
 iteratively updating the solution set until one or more stopping criteria are satisfied.   
     
     
         8 . The method of  claim 1 , wherein the optimization model is initialized with a set of random production targets representing the solution set. 
     
     
         9 . The method of  claim 1 , further comprising defining the optimization model to include a set of decision variables that include production targets for each of the one or more wells;
 defining the optimization model to include at least two objectives including maximizing a molecular weight of the flash gas (MWF) and maximizing oil production (Q oil ); and   defining the optimization model to include a set of constraints including at least one of a minimum reservoir pressure, one or more well-specific production targets, a total gas production limit, and a reservoir pressure minimum for maintaining above a bubble point.   
     
     
         10 . A system configured for controlling hydrocarbon production in one or more wells, the system comprising:
 at least one processor; and   a memory storing one or more instructions that, when executed by the at least one processor, cause the at least one processor to perform operations comprising:
 receiving, from one or more sensors of one or more wells, well data representing operation of the one or more wells; 
 retrieving an optimization model defined based on a plurality of operational parameters of the one or more wells, the operational parameters specifying operational constraints for each of the one or more wells; 
 processing, by the optimization model, the well data and generating a solution set of operational states for each of the one or more wells that optimizes hydrocarbon production at each of the one or more wells; 
 based on the processing, selecting, from the solution set, at least one solution that specifies an operational state for each of the one or more wells, the operational state optimizing the hydrocarbon production for that well of the one or more wells; 
 generating, for the one or more wells, instructions for controlling well production; and 
 sending, to the one or more wells, the instructions. 
   
     
     
         11 . The system of  claim 10 , the operations further comprising controlling, based on the instructions, well production at the one or more wells. 
     
     
         12 . The system of  claim 10 , wherein the optimization model is configured to maximize a molecular weight of a flash gas (MWF) for a well of the one or more wells or for a group of wells of the one or more wells. 
     
     
         13 . The system of  claim 10 , wherein the operational parameters comprise, for a given well of the one or more wells, a flowing bottom hole reservoir pressure, a bubble point pressure, and an initial production rate (TR). 
     
     
         14 . The system of  claim 10 , wherein the at least one solution includes a higher-ranking solution in the solution set, the higher-ranking solution being ranked higher than at least one lower-ranked solution in the solution set. 
     
     
         15 . The system of  claim 10 , wherein the well data comprises at least one of a flow rate in a wellbore of a well of the one or more wells, a wellbore pressure of the well of the one or more wells, a wellbore temperature of the well of the one or more wells, a fluid composition associated with the well of the one or more wells, and a well depth of the well of the one or more wells. 
     
     
         16 . The system of  claim 10 , wherein processing, by the optimization model, the well data comprises tracking one or more Pareto-optimal solutions of the solution set; and
 iteratively updating the solution set until one or more stopping criteria are satisfied.   
     
     
         17 . The system of  claim 10 , wherein the optimization model is initialized with a set of random production targets representing the solution set. 
     
     
         18 . The system of  claim 10 , the operations further comprising defining the optimization model to include a set of decision variables that include production targets for each of the one or more wells;
 defining the optimization model to include at least two objectives including maximizing a molecular weight of the flash gas (MWF) and maximizing oil production (Q oil ); and   defining the optimization model to include a set of constraints including at least one of a minimum reservoir pressure, one or more well-specific production targets, a total gas production limit, and a reservoir pressure minimum for maintaining above a bubble point.   
     
     
         19 . One or more non-transitory computer readable media storing one or more instructions configured for controlling hydrocarbon production in one or more wells, the one or more instructions causing at least one processor, when executing the one or more instructions, to perform operations comprising:
 receiving, from one or more sensors of one or more wells, well data representing operation of the one or more wells;   retrieving an optimization model defined based on a plurality of operational parameters of the one or more wells, the operational parameters specifying operational constraints for each of the one or more wells;   processing, by the optimization model, the well data and generating a solution set of operational states for each of the one or more wells that optimizes hydrocarbon production at each of the one or more wells;   based on the processing, selecting, from the solution set, at least one solution that specifies an operational state for each of the one or more wells, the operational state optimizing the hydrocarbon production for that well of the one or more wells; and   generating, for the one or more wells, instructions for controlling well production; and   sending, to the one or more wells, the instructions.   
     
     
         20 . The one or more non-transitory computer readable media of  claim 19 , the operations further comprising controlling, based on the instructions, well production at the one or more wells.