Ai-enabled unconfined compressive strength (ucs) real-time prediction utilizing logging-while-drilling measurements

Abstract

A method for optimizing a drilling performance of a drilling operation, based process data. The method includes obtaining process data while conducting a drilling operation through a subsurface, where the drilling operation is controlled by a set of drilling parameters, and determining, with a computational model that receives the process data as input, a real-time unconfined compressive strength (UCS) of the subsurface. The method further includes determining, based on the real-time UCS of the subsurface, a drilling performance of the drilling operation, and, upon determining that the drilling performance is not optimum, adjusting one or more drilling parameters, within the set of drilling parameters, to optimize the drilling performance.

What is claimed: 
     
         1 . A method, comprising:
 obtaining process data while conducting a drilling operation through a subsurface, wherein the drilling operation is controlled by a set of drilling parameters;   determining, with a computational model that receives the process data as input, a real-time unconfined compressive strength (UCS) of the subsurface;   determining, based on the real-time UCS of the subsurface, a drilling performance of the drilling operation; and   upon determining that the drilling performance is not optimum, adjusting one or more drilling parameters, within the set of drilling parameters, to optimize the drilling performance.   
     
     
         2 . The method of  claim 1 , wherein:
 the set of drilling parameters comprises one or more of:
 a weight-on-bit on a drill bit, 
 a torque of the drill bit, and 
 a mud flow rate; 
   the drilling performance is based on one or more of:
 a rate of penetration, and 
 an estimate of a drill bit life cycle; and 
   optimizing the drilling performance comprises one or more of:
 maximizing the rate of penetration, and 
 minimizing bit-runs. 
   
     
     
         3 . The method of  claim 1 , wherein the process data comprise logging-while-drilling (LWD) data, comprising one or more of:
 a gamma ray of the subsurface,   a bulk formation density of the subsurface; and   a thermal neutron porosity of the subsurface.   
     
     
         4 . The method of  claim 3 , wherein:
 the process data further comprise a sonic compressional wave propagation slowness (DTC) of the subsurface; and   the computational model comprises a physical model that receives the DTC of the subsurface and outputs the real-time UCS of the subsurface.   
     
     
         5 . The method of  claim 4 , wherein the computational model further comprises an artificial intelligence (AI) model that receives the LWD data and outputs the DTC of the subsurface. 
     
     
         6 . The method of  claim 5 , wherein:
 the computational model further comprises a petrophysical model that receives the LWD data and outputs a set of petrophysical data; and   the AI model further receives the set of petrophysical data.   
     
     
         7 . The method of  claim 6 , wherein the petrophysical data comprise one or more of:
 a total porosity of the subsurface; and   a volume of hydrocarbon gases within the subsurface.   
     
     
         8 . The method of  claim 7 , further comprising:
 obtaining training process data and a training DTC for each well within a plurality of existing wells;   constructing a training dataset of training examples, each training example comprising:
 training process data for a well within plurality of existing wells, and 
 a training DTC for the well; and 
   training the AI model using the training dataset.   
     
     
         9 . The method of  claim 5 , wherein the AI model comprises a random forest. 
     
     
         10 . A system, comprising:
 a drilling system performing a drilling operation through a subsurface, wherein:
 the drilling operation is controlled by a set of drilling parameters; and 
 the drilling system comprises:
 a drilling rig, 
 a drill string, connected to the drilling rig, and 
 a drill bit, connected to the drill string; 
 
   a plurality of sensors, connected to the drilling system, the plurality of sensors collecting process data from the drilling operation; and   a computer, configured to:
 receive the process data from the plurality of sensors, 
 determine, with a computational model that receives the process data as input, a real-time unconfined compressive strength (UCS) of the subsurface, 
 determine, based on the real-time UCS of the subsurface, a drilling performance of the drilling operation, and 
 upon determining that the drilling performance is not optimum, adjust one or more drilling parameters, within the set of drilling parameters, to optimize the drilling performance. 
   
     
     
         11 . The system of  claim 10 , wherein:
 the set of drilling parameters comprises one or more of:
 a weight-on-bit on the drill bit, 
 a torque of the drill bit, and 
 a mud flow rate; 
   the drilling performance is based on one or more of:
 a rate of penetration, and 
 an estimate of a drill bit life cycle; and 
   optimizing the drilling performance comprises one or more of:
 maximizing the rate of penetration, and 
 minimizing bit-runs. 
   
     
     
         12 . The system of  claim 10 , wherein the process data comprise logging-while-drilling (LWD) data, comprising one or more of:
 a gamma ray of the subsurface,   a bulk formation density of the subsurface; and   a thermal neutron porosity of the subsurface.   
     
     
         13 . The system of  claim 12 , wherein:
 the process data further comprise a sonic compressional wave propagation slowness (DTC) of the subsurface; and   the computational model comprises a physical model that receives the DTC of the subsurface and outputs the real-time UCS of the subsurface.   
     
     
         14 . The system of  claim 13 , wherein the computational model further comprises an artificial intelligence (AI) model that receives the LWD data and outputs the DTC of the subsurface. 
     
     
         15 . The system of  claim 14 , wherein:
 the computational model further comprises a petrophysical model that receives the LWD data and outputs a set of petrophysical data; and   the AI model further receives the set of petrophysical data.   
     
     
         16 . The system of  claim 15 , wherein the petrophysical data comprise one or more of:
 a total porosity of the subsurface; and   a volume of hydrocarbon gases within the subsurface.   
     
     
         17 . The system of  claim 16 , wherein the computer is further configured to:
 receive training process data and a training DTC for each well within a plurality of existing wells;   construct a training dataset of training examples, each training example comprising:
 training process data for a well within plurality of existing wells, and 
 a training DTC for the well; and 
   train the AI model using the training dataset.   
     
     
         18 . The system of  claim 14 , wherein the AI model comprises a random forest. 
     
     
         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 process data while conducting a drilling operation through a subsurface, wherein the drilling operation is controlled by a set of drilling parameters;   determining, with a computational model that receives the process data as input, a real-time unconfined compressive strength (UCS) of the subsurface;   determining, based on the real-time UCS of the subsurface, a drilling performance of the drilling operation; and   upon determining that the drilling performance is not optimum, adjusting one or more drilling parameters, within the set of drilling parameters, to optimize the drilling performance.   
     
     
         20 . The non-transitory computer-readable memory of  claim 19 , wherein:
 the process data comprise logging-while-drilling (LWD) data;   the computational model comprises:
 an artificial intelligence (AI) model that receives the LWD data and outputs a sonic compressional wave propagation slowness (DTC) of the subsurface, and 
 a physical model that receives the DTC of the subsurface and outputs the real-time UCS of the subsurface; 
   the set of drilling parameters comprises one or more of:
 a weight-on-bit on a drill bit, 
 a torque of the drill bit, and 
 a mud flow rate; 
   the drilling performance is based on one or more of:
 a rate of penetration, and 
 an estimate of a drill bit life cycle; 
   optimizing the drilling performance comprises one or more of:
 maximizing the rate of penetration, and
 minimizing bit-runs; and 
 
   the LWD data comprises one or more of:
 a gamma ray of the subsurface, 
 a bulk formation density of the subsurface; and 
 a thermal neutron porosity of the subsurface.