Well chemical injection control

Abstract

A method can include receiving data for a well; determining a gas flow rate and a liquid level for the well; determining an amount of chemical to inject into the well based on the gas flow rate and the liquid level; and issuing a signal to chemical injection equipment to inject the amount of chemical into the well.

What is claimed is: 
     
         1 . A method comprising:
 receiving data for a well;   determining a gas flow rate and a liquid level for the well;   determining an amount of chemical to inject into the well based on the gas flow rate and the liquid level; and   issuing a signal to chemical injection equipment to inject the amount of chemical into the well.   
     
     
         2 . The method of  claim 1 , wherein the chemical comprises a surfactant. 
     
     
         3 . The method of  claim 1 , wherein the chemical generates foam. 
     
     
         4 . The method of  claim 1 , wherein the amount of chemical facilitates gas production from the well. 
     
     
         5 . The method of  claim 1 , wherein a higher liquid level corresponds to a greater amount of the chemical. 
     
     
         6 . The method of  claim 1 , wherein the data comprise gas flow meter measurement data. 
     
     
         7 . The method of  claim 6 , wherein the gas flow meter measurement data are indicative of the gas flow rate. 
     
     
         8 . The method of  claim 1 , wherein the data comprise downhole gauge data. 
     
     
         9 . The method of  claim 8 , wherein the downhole gauge data are indicative of the liquid level. 
     
     
         10 . The method of  claim 1 , wherein the data comprise one or more of tubing head pressure and casing head pressure. 
     
     
         11 . The method of  claim 10 , wherein the data are indicative of liquid level. 
     
     
         12 . The method of  claim 1 , wherein determining the liquid level comprises implementing a trained machine learning model. 
     
     
         13 . The method of  claim 12 , comprising generating the trained machine learning model using data from one or more wells. 
     
     
         14 . The method of  claim 12 , wherein the trained machine learning model operates on input that comprises one or more of tubing head pressure and casing head pressure. 
     
     
         15 . The method of  claim 1 , wherein the chemical injection equipment comprises a manifold for injection of the chemical into one or more wells. 
     
     
         16 . The method of  claim 1 , comprising determining an amount of chemical to inject into another well. 
     
     
         17 . The method of  claim 1 , wherein the method is performed using a computational framework operatively coupled to the chemical injection equipment. 
     
     
         18 . The method of  claim 17 , wherein the computational framework is local and/or remote from a site of the well. 
     
     
         19 . A system comprising:
 one or more processors;   memory accessible to the one or more processors;   processor-executable instructions stored in the memory and executable to instruct the system to:
 receive data for a well; 
 determine a gas flow rate and a liquid level for the well; 
 determine an amount of chemical to inject into the well based on the gas flow rate and the liquid level; and 
 issue a signal to chemical injection equipment to inject the amount of chemical into the well. 
   
     
     
         20 . One or more computer-readable media comprising computer-executable instructions executable by a system to instruct the system to:
 receive data for a well;   determine a gas flow rate and a liquid level for the well;   determine an amount of chemical to inject into the well based on the gas flow rate and the liquid level; and   issue a signal to chemical injection equipment to inject the amount of chemical into the well.