Data driven descaling

Abstract

A computer implemented method that enables data driven descaling is described. The method includes obtaining data associated with a descaling target and deriving engineered features from the data associated with the descaling target. A machine learning model is selected and trained to predict the use of chemical descaling operations or mechanical descaling operations using the engineered features.

What is claimed is: 
     
         1 . A computer-implemented method that enables data driven descaling, comprising:
 obtaining, using at least one hardware processor, data associated with a descaling target;   deriving, using the at least one hardware processor, engineered features from the data associated with the descaling target, wherein the engineered features are created based on patterns found in the data associated with the descaling target; and   training, using the at least one hardware processor, a selected machine learning model to predict use of chemical descaling operations or mechanical descaling operations based on the engineered features.   
     
     
         2 . The computer implemented method of  claim 1 , wherein the selected machine learning model is trained to predict a number of coiled tubes used in the chemical descaling operations or the mechanical descaling operations. 
     
     
         3 . The computer implemented method of  claim 1 , wherein the descaling target is a well and the selected machine learning model is trained to predict the use of chemical descaling operations or mechanical descaling operations for a drilled interval of the well using the engineered features and a number of coiled tubes used in the chemical descaling operations or the mechanical descaling operations. 
     
     
         4 . The computer implemented method of  claim 1 , pre-processing the data associated with the descaling target to removing outliers and insert missing data. 
     
     
         5 . The computer implemented method of  claim 1 , iteratively training the trained, selected machine learning model to enhance model accuracy. 
     
     
         6 . The computer implemented method of  claim 1 , rendering a visualization that shows output of the trained, selected machine learning model that shows predicted descaling operations for at least one interval of a drilled well. 
     
     
         7 . The computer implemented method of  claim 1 , wherein the selected machine learning model is selected from machine learning models trained to predict the use of chemical descaling operations or mechanical descaling operations. 
     
     
         8 . An apparatus comprising a non-transitory, computer readable, storage medium that stores instructions that, when executed by at least one processor, cause the at least one processor to perform operations comprising:
 obtaining data associated with a descaling target;   deriving engineered features from the data associated with the descaling target, wherein the engineered features are created based on patterns found in the data associated with the descaling target; and   training a selected machine learning model to predict use of chemical descaling operations or mechanical descaling operations based on the engineered features.   
     
     
         9 . The apparatus of  claim 8 , wherein the selected machine learning model is trained to predict a number of coiled tubes used in the chemical descaling operations or the mechanical descaling operations. 
     
     
         10 . The apparatus of  claim 8 , wherein the descaling target is a well and the selected machine learning model is trained to predict the use of chemical descaling operations or mechanical descaling operations for a drilled interval of the well using the engineered features and a number of coiled tubes used in the chemical descaling operations or the mechanical descaling operations. 
     
     
         11 . The apparatus of  claim 8 , pre-processing the data associated with the descaling target to removing outliers and insert missing data. 
     
     
         12 . The apparatus of  claim 8 , iteratively training the trained, selected machine learning model to enhance model accuracy. 
     
     
         13 . The apparatus of  claim 8 , rendering a visualization that shows output of the trained, selected machine learning model that shows predicted descaling operations for at least one interval of a drilled well. 
     
     
         14 . The apparatus of  claim 8 , wherein the selected machine learning model is selected from machine learning models trained to predict the use of chemical descaling operations or mechanical descaling operations. 
     
     
         15 . A system, comprising:
 one or more memory modules;   one or more hardware processors communicably coupled to the one or more memory modules, the one or more hardware processors configured to execute instructions stored on the one or more memory modules to perform operations comprising:   obtaining data associated with a descaling target;   deriving engineered features from the data associated with the descaling target, wherein the engineered features are created based on patterns found in the data associated with the descaling target; and   training a selected machine learning model to predict use of chemical descaling operations or mechanical descaling operations based on the engineered features.   
     
     
         16 . The system of  claim 15 , wherein the selected machine learning model is trained to predict a number of coiled tubes used in the chemical descaling operations or the mechanical descaling operations. 
     
     
         17 . The system of  claim 15 , wherein the descaling target is a well and the selected machine learning model is trained to predict the use of chemical descaling operations or mechanical descaling operations for a drilled interval of the well using the engineered features and a number of coiled tubes used in the chemical descaling operations or the mechanical descaling operations. 
     
     
         18 . The system of  claim 15 , pre-processing the data associated with the descaling target to removing outliers and insert missing data. 
     
     
         19 . The system of  claim 15 , iteratively training the trained, selected machine learning model to enhance model accuracy. 
     
     
         20 . The system of  claim 15 , rendering a visualization that shows output of the trained, selected machine learning model that shows predicted descaling operations for at least one interval of a drilled well.