System and method for predicting and optimizing drilling parameters

Abstract

A method and a system for using machine learning technologies to predict the value and timing of operational parameters. These predictions are then used to optimize the rate of penetration (ROP) of a drilling operation.

1 . A method for predicting drilling parameters for drilling operation, the method comprising:
 receiving time-based data from a real-time data system including a sensor;   filtering the time-based data from the system;   generating, using a machine learning model, predictions based on the filtered time-based data from the sensor, wherein the predictions include a predicted rate of penetration; and   selecting drilling parameters that yield the highest predicted rate of penetration.   
     
     
         2 . The method of  claim 1 , wherein the predictions include one or more of weight on bit, revolutions per minute and mud flow. 
     
     
         3 . The method of  claim 1 , wherein the time-based data includes one or more of rate of penetration, weight on bit, revolutions per minute and mud flow. 
     
     
         4 . The method of  claim 3 , wherein the time-based data is received at a processor remote from the oil well. 
     
     
         5 . The method of  claim 4 , wherein the processor calculates the average values for one or more sensor values over a time interval or a depth interval. 
     
     
         6 . The method of  claim 4 , wherein one or more machine learning models predict values of one or more of rate of penetration, weight on bit, revolutions per minute, and mud flow based on the measured time-based data averaged time-based data or logarithmic values of the time-based data. 
     
     
         7 . (canceled) 
     
     
         8 . The method of  claim 4 , wherein an algorithm stepwise modifies the measured sensor values and a machine learning model makes a new prediction for each modification. 
     
     
         9 . The method of  claim 6 , wherein predictions are repeated one or more times during the operational sequence. 
     
     
         10 . The method of  claim 1 , wherein one or more of the predicted weight on bit, revolutions per minute and mud flow yielding the highest rate of penetration is selected. 
     
     
         11 . The method of  claim 10 , wherein the predicted weight on bit, revolutions per minute and mud flow yielding the highest rate of penetration is compared with threshold values of said parameters. 
     
     
         12 . The method of  claim 11 , wherein a different rate of penetration and associated parameters is selected if one or more of the parameters exceeds the threshold values. 
     
     
         13 . The method of  claim 1 , wherein the predicted data values are converted to time or depth series data and stored in a database and/or visualized in a computer user interface. 
     
     
         14 . (canceled) 
     
     
         15 . The method of  claim 1 , wherein drilling operations are identified by filtering two or more sensors. 
     
     
         16 . The method of  claim 1 , wherein two or more machine learning models utilize the same filtered and normalized data sets and a selection algorithm selects a single preferred prediction data series. 
     
     
         17 . A system for predicting rate of penetration in oilfield operations comprising:
 a real time data system associated with at least one oil well;   an electronic processor and a memory, the memory storing instructions that when executed by the electronic processor configure the electronic processor to:
 receive data from the real time data system; 
 filtering the time-based data from the system;
 generating, using a machine learning model, predictions based on the filtered time-based data from the sensor, wherein the predictions include a predicted rate of penetration; and 
 
 selecting drilling parameters that yield the highest predicted rate of penetration. 
   
     
     
         18 . The system of  claim 17 , wherein the real time data system comprises one or more sensors associated with an oil well. 
     
     
         19 . The system of  claim 17 , wherein the processor configured to receive data from the real time data system is remote from the oil well. 
     
     
         20 . The system of  claim 17 , wherein the time measured, predicted drilling parameters, and rate of penetration are visualized in a user interface which may be located remote from the oil well or on-site. 
     
     
         21 . (canceled) 
     
     
         22 . The system of  claim 17 , wherein the predicted drilling parameters and rate of penetration are converted to time or depth series data and stored in a database. 
     
     
         23 . (canceled) 
     
     
         24 . (canceled) 
     
     
         25 . (canceled) 
     
     
         26 . The system of  claim 17 , wherein the instructions executed by the electronic processor is containerized and deployed to a virtual machine in a data center or on a physical server. 
     
     
         27 . (canceled)