Downhole valve optimization for pump intake pressure using machine learning

Abstract

A method that includes obtaining static and dynamic well data for a well. The static well data describes well design parameters and the static well data describes well properties that change over time. The method includes obtaining first choke index setting data regarding a first choke disposed in a producing zone of the well. The method includes using a recurrent neural network to generate, by a computer processor, first predicted electrical submersible pump (ESP) input data for an ESP in hydraulic connection with the first choke based on the static and dynamic well data, and the first choke index setting data. The method includes determining well performance data for the well based on the predicted ESP input data. The method includes determining well operations for the well based on the well performance data and transmitting a command to a control system that causes the well operations to be performed.

What is claimed: 
     
         1 . A method, comprising:
 obtaining static well data for a well,
 wherein the static well data describes one or more well design parameters of the well; 
   obtaining dynamic well data for the well,
 wherein the dynamic well data describes one or more well properties that change over time; 
   obtaining first choke index setting data regarding a first choke disposed in a producing zone of interest of the well;   generating, by a computer processor, first predicted electrical submersible pump (ESP) input data for a first ESP in hydraulic connection with the first choke based on the static well data, the dynamic well data, and the first choke index setting data using a recurrent neural network;   determining, by the computer processor, well performance data for the well based on the first predicted ESP input data;   determining, by the computer processor, well operations for the well based on the well performance data; and   transmitting, by the computer processor and to a control system coupled to the well, a command that causes the well operations to be performed at the well.   
     
     
         2 . The method of  claim 1 ,
 wherein the recurrent neural network is a long short-term memory (LSTM) network.   
     
     
         3 . The method of  claim 1 ,
 wherein determining the well performance data comprises:   simulating the well using a reservoir simulator based on the first predicted ESP input data.   
     
     
         4 . The method of  claim 1 , further comprising:
 determining an optimal first choke index setting for the first choke based on one or more of the first predicted ESP input data and the first predicted well performance data,   wherein the well operations comprise adjusting the first choke index setting to the optimal choke index setting,   wherein the optimal first choke index setting comprises a cross-sectional flow area of a flowpath between the producing zone of interest and an ESP flow inlet.   
     
     
         5 . The method of  claim 1 ,
 wherein the dynamic well data and the first choke index setting data are acquired simultaneously from the well.   
     
     
         6 . The method of  claim 1 , further comprising:
 generating, by the computer processor, predicted ESP maintenance data for the first ESP using the static well data, the dynamic well data, the first choke index setting data, and the recurrent neural network.   
     
     
         7 . The method of  claim 1 ,
 wherein the well operations comprise an ESP maintenance operation, an ESP frequency input change, or a choke index setting change.   
     
     
         8 . The method of  claim 1 ,
 wherein the first choke index setting data comprises flowrate data and pressure data from respective entities of a plurality of index settings.   
     
     
         9 . The method of  claim 1 , further comprising:
 determining, using the recurrent neural network, second predicted ESP input data for a second ESP in hydraulic connection with a second choke disposed in a second producing zone of the well, wherein the well performance data is determined based on the first and second predicted ESP input data; and   determining a priority ranking for the well operations based on the well performance data,   wherein the command that causes the well operations is based on the priority ranking.   
     
     
         10 . A system, comprising:
 a well control system coupled to a well at a well site, wherein the well comprises a plurality of choke components that are installed in a wellbore; and   a well performance manager coupled to the well control system, the well performance manager comprising a computer processor, wherein the well performance manager is configured to perform a method comprising:
 obtaining static well data for a well,
 wherein the static well data describes one or more well design parameters of the well; 
 
 obtaining dynamic well data for the well,
 wherein the dynamic well data describes one or more well properties that change over time; 
 
 obtaining first choke index setting data regarding a first choke comprised by the plurality of choke components, the first choke disposed in a producing zone of interest of the well; 
 generating first predicted electrical submersible pump (ESP) input data for a first ESP in hydraulic connection with the first choke based on the static well data, the dynamic well data, and the first choke index setting data using a recurrent neural network; 
 determining well performance data for the well based on the first predicted ESP input data; 
 determining well operations for the well based on the well performance data; and 
 transmitting to the well control system a command that causes the well operations to be performed at the well. 
   
     
     
         11 . The system of  claim 10 ,
 wherein the recurrent neural network is a long short-term memory (LSTM) network.   
     
     
         12 . The system of  claim 10 ,
 wherein determining the well performance data comprises:
 simulating the well using a reservoir simulator based on the first predicted ESP input data. 
   
     
     
         13 . The system of  claim 10 , the well performance manager further configured to perform:
 determining an optimal first choke index setting for the first choke based on one or more of the first predicted ESP input data and the first predicted well performance data,   wherein the well operations comprise adjusting the first choke index setting to the optimal choke index setting,   wherein the optimal first choke index setting comprises a cross-sectional flow area of a flowpath between the producing zone of interest and an ESP flow inlet.   
     
     
         14 . The system of  claim 10 ,
 wherein the dynamic well data and the first choke index setting data are acquired simultaneously from the well.   
     
     
         15 . The system of  claim 10 , the well performance manager further configured to perform:
 generating predicted ESP maintenance data for the first ESP using the static well data, the dynamic well data, the first choke index setting data, and the recurrent neural network.   
     
     
         16 . The system of  claim 10 ,
 wherein the well operations comprise an ESP maintenance operation, an ESP frequency input change, or a choke index setting change.   
     
     
         17 . The system of  claim 10 ,
 wherein the first choke index setting data comprises flowrate data and pressure data from respective entities of a plurality of index settings.   
     
     
         18 . The system of  claim 10 , the well performance manager further configured to perform:
 determining, using the recurrent neural network, second predicted ESP input data for a second ESP in hydraulic connection with a second choke disposed in a second producing zone of the well, wherein the well performance data is determined based on the first and second predicted ESP input data; and   determining a priority ranking for the well operations based on the well performance data,   wherein the command that causes the well operations is based on the priority ranking.   
     
     
         19 . A non-transitory computer-readable memory comprising computer-executable instructions stored thereon that, when executed on a processor, cause the processor to perform steps comprising:
 obtaining static well data for a well,
 wherein the static well data describes one or more well design parameters of the well; 
   obtaining dynamic well data for the well,
 wherein the dynamic well data describes one or more well properties that change over time; 
   obtaining first choke index setting data regarding a first choke disposed in a producing zone of interest of the well;   generating first predicted electrical submersible pump (ESP) input data for a first ESP in hydraulic connection with the first choke based on the static well data, the dynamic well data, and the first choke index setting data using a recurrent neural network;   determining well performance data for the well based on the first predicted ESP input data;   determining well operations for the well based on the well performance data; and   transmitting to a control system coupled to the well a command that causes the well operations to be performed at the well.   
     
     
         20 . The non-transitory computer-readable memory of  claim 19 ,
 wherein determining the well performance data comprises:
 simulating the well using a reservoir simulator based on the first predicted ESP input data.