Method and system for classifying and detecting true well control events during drilling operations

Abstract

The invention relates to method and system for classifying events (well control events) during drilling operations. The method includes determining drilling attributes corresponding to volve drilling data in a predefined format and associated with one or more wells; determining a correlation value between each two attributes of the drilling attributes associated with the volve drilling data; selecting a set of drilling attributes from the drilling attributes based the determined correlation value; generating a labelled dataset corresponding to the volve drilling data based on the set of drilling attributes by determining a value of one or more additional drilling attributes associated with the volve drilling data based on the set of drilling attributes; and training a supervised Machine Learning (ML) model based on the labelled dataset and real-time drilling data for classifying each of the one or more drillings events in one of a set of pre-defined categories.

What is claimed is: 
     
         1 . A method for classifying events during drilling operations, the method comprising:
 determining, by an event determination device, a plurality of drilling attributes corresponding to volve drilling data in a predefined format and associated with one or more wells, wherein the volve drilling data is associated with one or more drilling operations;   determining, by the event determination device, a correlation value between each two attributes of the plurality of drilling attributes associated with the volve drilling data;   selecting, by the event determination device, a set of drilling attributes from the plurality of drilling attributes based the determined correlation value;   generating, by the event determination device, a labelled dataset corresponding to the volve drilling data based on the set of drilling attributes, wherein generating the labelled dataset comprises:
 determining a value of one or more additional drilling attributes associated with the volve drilling data based on the set of drilling attributes; and 
   training, by the event determination device, a supervised Machine Learning (ML) model based on the labelled dataset and real-time drilling data for classifying each of the one or more drillings events in one of a set of pre-defined categories.   
     
     
         2 . The method of  claim 1 , wherein the set of drilling attributes comprises a bit depth, a hole depth, a mud flow rate out, an average hook load, an average rate of penetration, an average weight on bit, a total pump stroke rate, and a rig activity code. 
     
     
         3 . The method of  claim 1 , wherein the one or more additional drilling attributes comprise a mud weight, and a pore pressure. 
     
     
         4 . The method of  claim 1 , wherein determining the plurality of drilling attributes further comprises:
 extracting the volve drilling data associated with the one or more wells, in a current format; and   pre-processing the volve drilling data to convert the current format into the predefined format through a data pre-processing technique, wherein the predefined format comprises a Comma Separated Values (CSV) format.   
     
     
         5 . The method of  claim 1 , wherein the supervised ML model is a Random Forest Classifier (RFC) model. 
     
     
         6 . The method of  claim 1 , wherein the set of pre-defined categories comprises a kick category and a non-kick category. 
     
     
         7 . The method of  claim 6 , further comprising:
 receiving, by the trained supervised ML model, real-time data corresponding a drilling operation; and   determining, by the trained supervised ML model, at least one of the kick category or the non-kick category for each of a set of drilling events associated with the drilling operation based on the real-time data and historical data, wherein determining the kick category or the non-kick category for each of the set of drilling events comprises:
 calculating a value of the one or more additional drilling attributes corresponding to the real-time data based on the set of drilling attributes. 
   
     
     
         8 . The method of  claim 1 , wherein selecting the set of drilling attributes comprises eliminating one or more drilling attributes with high correlation values based on a predefined correlation threshold value, wherein high correlation values comprise one of a high positive correlation value or a high negative correlation value. 
     
     
         9 . A system for classifying events during drilling operations, the system comprising:
 a processor; and   a memory communicatively coupled to the processor, wherein the memory stores processor-executable instructions, which, on execution, cause the processor to:
 determine a plurality of drilling attributes corresponding to volve drilling data in a predefined format and associated with one or more wells, wherein the volve drilling data is associated with one or more drilling events; 
 determine a correlation value between each two attributes of the plurality of drilling attributes associated with the volve drilling data; 
 select a set of drilling attributes from the plurality of drilling attributes based the determined correlation value; 
 generate a labelled dataset corresponding to the volve drilling data based on the set of drilling attributes, wherein generating the labelled dataset comprises:
 determine a value of one or more additional drilling attributes associated with the volve drilling data based on the set of drilling attributes; and 
 
 train a supervised Machine Learning (ML) model based on the labelled dataset and real-time drilling data for classifying each of the one or more drillings events in one of a set of pre-defined categories. 
   
     
     
         10 . The system of  claim 9 , wherein the set of drilling attributes comprises a bit depth, a hole depth, a mud flow rate out, an average hook load, an average rate of penetration, an average weight on bit, a total pump stroke rate, and a rig activity code. 
     
     
         11 . The system of  claim 9 , wherein the one or more additional drilling attributes comprise a mud weight, and a pore pressure. 
     
     
         12 . The system of  claim 9 , wherein the processor-executable instructions further cause the processor to:
 extract the volve drilling data associated with the one or more wells, in a current format; and   pre-process the volve drilling data to convert the current format into the predefined format through a data pre-processing technique, wherein the predefined format comprises a Comma Separated Values (CSV) format.   
     
     
         13 . The system of  claim 9 , wherein the supervised ML model is a Random Forest Classifier (RFC) model. 
     
     
         14 . The system of  claim 9 , wherein the set of pre-defined categories comprises a kick category and a non-kick category. 
     
     
         15 . The system of  claim 14 , wherein the processor-executable instructions further cause the processor to:
 receive, by the trained supervised ML model, real-time data corresponding a drilling operation; and   determine, by the trained supervised ML model, at least one of the kick category or the non-kick category for each of a set of drilling events associated with the drilling operation based on the real-time data and historical data, wherein determining the kick category or the non-kick category for each of the set of drilling events comprises:
 calculate a value of the one or more additional drilling attributes corresponding to the real-time data based on the set of drilling attributes. 
   
     
     
         16 . The system of  claim 9 , wherein the processor-executable instructions further cause the processor to select the set of drilling attributes by eliminating one or more drilling attributes with high correlation values based on a predefined correlation threshold value, wherein high correlation values comprise one of a high positive correlation value or a high negative correlation value. 
     
     
         17 . A non-transitory computer-readable medium storing computer-executable instructions for computing a toolpath for classifying events during drilling operations, the computer-executable instructions configured for:
 determining a plurality of drilling attributes corresponding to volve drilling data in a predefined format and associated with one or more wells, wherein the volve drilling data is associated with one or more drilling events;   determining a correlation value between each two attributes of the plurality of drilling attributes associated with the volve drilling data;   selecting a set of drilling attributes from the plurality of drilling attributes based the determined correlation value;   generating a labelled dataset corresponding to the volve drilling data based on the set of drilling attributes, wherein generating the labelled dataset comprises:
 determining a value of one or more additional drilling attributes associated with the volve drilling data based on the set of drilling attributes; and 
   training a supervised Machine Learning (ML) model based on the labelled dataset and real-time drilling data for classifying each of the one or more drillings events in one of a set of pre-defined categories.   
     
     
         18 . The non-transitory computer-readable medium of the  claim 17 , wherein the computer-executable instructions further configured for determining the plurality of drilling attributes, by:
 extracting the volve drilling data associated with the one or more wells, in a current format; and   pre-processing the volve drilling data to convert the current format into the predefined format through a data pre-processing technique, wherein the predefined format comprises a Comma Separated Values (CSV) format.   
     
     
         19 . The non-transitory computer-readable medium of the  claim 17 , wherein the set of pre-defined categories comprises a kick category and a non-kick category. 
     
     
         20 . The non-transitory computer-readable medium of the  claim 19 , wherein the computer-executable instructions further configured for:
 receiving, by the trained supervised ML model, real-time data corresponding a drilling operation; and   determining, by the trained supervised ML model, at least one of the kick category or the non-kick category for each of a set of drilling events associated with the drilling operation based on the real-time data and historical data, wherein determining the kick category or the non-kick category for each of the set of drilling events comprises:
 calculating a value of the one or more additional drilling attributes corresponding to the real-time data based on the set of drilling attributes.