System and method for rapid mud loss diagnostics in fractured media

Abstract

A method of modeling a drilling mud loss behavior for a reservoir, including: receiving mud loss data for the reservoir; determining, using the mud loss data and a Latin Hypercube Sampling algorithm, a plurality of lost circulation events based on a plurality of uncertainty parameters; generating, using a semi-analytical function, a mud loss training dataset from the plurality of lost circulation events; training, using the mud loss training dataset, a machine learning model to predict a plurality of output parameters of lost circulation events; determining, using the mud loss data, a new lost circulation event based on the plurality of uncertainty parameters; determining, using the trained machine learning model, the plurality of output parameters of the new lost circulation event; and determining an operation to adjust a parameter of a drilling mud for the reservoir using the plurality of output parameters of the new lost circulation event.

What is claimed is: 
     
         1 . A method for modeling a drilling mud loss behavior for a reservoir, comprising:
 receiving mud loss data associated with the drilling mud loss behavior for the reservoir;   identifying, using the mud loss data, a plurality of uncertainty parameters associated with the drilling mud loss behavior for the reservoir;   determining, using the mud loss data and a Latin Hypercube Sampling (LHS) algorithm, a plurality of lost circulation events associated with the drilling mud loss behavior for the reservoir;   generating, using a semi-analytical function, a mud loss training dataset from the plurality of lost circulation events associated with the drilling mud loss behavior for the reservoir;   training, using the mud loss training dataset, a machine learning model to predict a maximum loss volume, a maximum stopping time, and an equivalent hydraulic fracture aperture associated with the drilling mud loss behavior for the reservoir;   determining, using the mud loss data, a new lost circulation event based on the plurality of uncertainty parameters associated with the drilling mud loss behavior for the reservoir, the new lost circulation event having a corresponding early loss volume and a corresponding early loss time;   determining, using the trained machine learning model, a new maximum loss volume, a new maximum stopping time, and a new equivalent hydraulic fracture aperture associated with the new lost circulation event based on the plurality of uncertainty parameters and the new lost circulation event; and   determining an operation to adjust a parameter of a drilling mud for the reservoir based on the maximum loss volume, the maximum stopping time, and the equivalent hydraulic fracture aperture associated with the new lost circulation event.   
     
     
         2 . The method of  claim 1 , wherein the plurality of uncertainty parameters comprise flow behavior index, fluid yield stress, average hydraulic fracture aperture, consistency factor, pressure drop, and wellbore radius, each of the plurality of uncertainty parameters having a corresponding value range. 
     
     
         3 . The method of  claim 1 , further comprising:
 determining, using the LHS algorithm, the plurality of lost circulation events associated with the drilling mud loss behavior for the reservoir based on a predetermined sampling number.   
     
     
         4 . The method of  claim 1 , further comprising:
 generating, using the semi-analytical function, a plurality of output solutions based on the plurality of lost circulation events associated with the drilling mud loss behavior for the reservoir, each of the plurality of output solutions comprising a corresponding early loss volume, a corresponding early loss time, a corresponding maximum loss volume, and a corresponding maximum stopping time.   
     
     
         5 . The method of  claim 4 , further comprising:
 generating the mud loss training dataset by combining the plurality of output solutions and the respective plurality of uncertainty parameters based on a predetermined threshold.   
     
     
         6 . The method of  claim 1 , further comprising:
 predicting a drilling mud behavior of leakage rate as a function of time for the reservoir based on the new maximum loss volume, the new maximum stopping time, and the new equivalent hydraulic fracture aperture associated with the new lost circulation event.   
     
     
         7 . The method of  claim 6 , further comprising:
 assessing, using the drilling mud behavior of leakage rate as a function of time for the reservoir, fracture conductivity for the reservoir.   
     
     
         8 . The method of  claim 1 , further comprising:
 training the machine learning model by implementing an Artificial Neural Network (ANN).   
     
     
         9 . The method of  claim 8 , further comprising:
 normalizing, using a min-max linear scale, input and output parameters of the machine learning model.   
     
     
         10 . The method of  claim 1 , further comprising:
 evaluating the machine learning model using a mean squared error (MSE) and a root mean square error (RMSE).   
     
     
         11 . The method of  claim 1 , wherein the operation comprises adjusting a property of the drilling mud or adjusting a pumping rate of the drilling mud. 
     
     
         12 . A system for modeling a drilling mud loss behavior for a reservoir, comprising:
 a processor; and   a computer-readable non-transitory storage medium comprising instructions that, when executed by the processor, cause to the processor to perform operations comprising:
 receiving mud loss data associated with the drilling mud loss behavior for the reservoir; 
 identifying, using the mud loss data, a plurality of uncertainty parameters associated with the drilling mud loss behavior for the reservoir; 
 determining, using the mud loss data and a Latin Hypercube Sampling (LHS) algorithm, a plurality of lost circulation events associated with the drilling mud loss behavior for the reservoir; 
 generating, using a semi-analytical function, a mud loss training dataset from the plurality of lost circulation events associated with the drilling mud loss behavior for the reservoir; 
 training, using the mud loss training dataset, a machine learning model to predict a maximum loss volume, a maximum stopping time, and an equivalent hydraulic fracture aperture associated with the drilling mud loss behavior for the reservoir; 
 determining, using the mud loss data, a new lost circulation event based on the plurality of uncertainty parameters associated with the drilling mud loss behavior for the reservoir, the new lost circulation event having a corresponding early loss volume and a corresponding early loss time; 
 determining, using the trained machine learning model, a new maximum loss volume, a new maximum stopping time, and a new equivalent hydraulic fracture aperture associated with the new lost circulation event based on the plurality of uncertainty parameters and the new lost circulation event; and 
 determining an operation to adjust a parameter of a drilling mud for the reservoir based on the maximum loss volume, the maximum stopping time, and the equivalent hydraulic fracture aperture associated with the new lost circulation event. 
   
     
     
         13 . The system of  claim 12 , wherein the plurality of uncertainty parameters comprise flow behavior index, fluid yield stress, average hydraulic fracture aperture, consistency factor, pressure drop, and wellbore radius, each of the plurality of uncertainty parameters having a corresponding value range. 
     
     
         14 . The system of  claim 12 , the operations further comprising:
 determining, using the LHS algorithm, the plurality of lost circulation events associated with the drilling mud loss behavior for the reservoir based on a predetermined sampling number.   
     
     
         15 . The system of  claim 12 , the operations further comprising:
 generating, using the semi-analytical function, a plurality of output solutions based on the plurality of lost circulation events associated with the drilling mud loss behavior for the reservoir, each of the plurality of output solutions comprising a corresponding early loss volume, a corresponding early loss time, a corresponding maximum loss volume, and a corresponding maximum stopping time.   
     
     
         16 . The system of  claim 15 , the operations further comprising:
 generating the mud loss training dataset by combining the plurality of output solutions and the respective plurality of uncertainty parameters based on a predetermined threshold.   
     
     
         17 . The system of  claim 12 , the operations further comprising:
 predicting a drilling mud behavior of leakage rate as a function of time for the reservoir based on the new maximum loss volume, the new maximum stopping time, and the new equivalent hydraulic fracture aperture associated with the new lost circulation event; and   assessing, using the drilling mud behavior of leakage rate as a function of time for the reservoir, fracture conductivity for the reservoir.   
     
     
         18 . The system of  claim 12 , the operations further comprising:
 normalizing, using a min-max linear scale, input and output parameters of the machine learning model;   training the machine learning model by implementing an Artificial Neural Network (ANN); and   evaluating the machine learning model using a mean squared error (MSE) and a root mean square error (RMSE).   
     
     
         19 . The system of  claim 12 , wherein the operation comprises adjusting a property of the drilling mud or adjusting a pumping rate of the drilling mud. 
     
     
         20 . A non-transitory computer-readable medium comprising instructions, when executed by a processor, cause the processor to perform operations comprising:
 receiving mud loss data associated with the drilling mud loss behavior for the reservoir;   identifying, using the mud loss data, a plurality of uncertainty parameters associated with the drilling mud loss behavior for the reservoir;   determining, using the mud loss data and a Latin Hypercube Sampling (LHS) algorithm, a plurality of lost circulation events associated with the drilling mud loss behavior for the reservoir;   generating, using a semi-analytical function, a mud loss training dataset from the plurality of lost circulation events associated with the drilling mud loss behavior for the reservoir;   training, using the mud loss training dataset, a machine learning model to predict a maximum loss volume, a maximum stopping time, and an equivalent hydraulic fracture aperture associated with the drilling mud loss behavior for the reservoir;   determining, using the mud loss data, a new lost circulation event based on the plurality of uncertainty parameters associated with the drilling mud loss behavior for the reservoir, the new lost circulation event having a corresponding early loss volume and a corresponding early loss time;   determining, using the trained machine learning model, a new maximum loss volume, a new maximum stopping time, and a new equivalent hydraulic fracture aperture associated with the new lost circulation event based on the plurality of uncertainty parameters and the new lost circulation event; and   determining an operation to adjust a parameter of a drilling mud for the reservoir based on the maximum loss volume, the maximum stopping time, and the equivalent hydraulic fracture aperture associated with the new lost circulation event.