Drilling optimization using acoustic signals

Abstract

Disclosed are methods, systems, and computer-readable medium to perform operations including: obtaining sensor data from at least one sensor attached to a surface of a drill bit; providing the sensor data from the at least one sensor to one or more machine learning models, wherein the one or more machine learning models are trained using a library of (i) sensor signatures and (ii) geological formations to output one or more drilling parameters; and adjusting one or more parameters of an operation performed by a drill controlling the drill bit based on the one or more drilling parameters output by one or more machine learning models.

What is claimed is: 
     
         1 . A method comprising:
 obtaining sensor data from at least one sensor attached to a surface of a drill bit;   providing the sensor data from the at least one sensor to one or more machine learning models, wherein the one or more machine learning models are trained using a library of (i) sensor signatures and (ii) geological formations to output one or more drilling parameters; and   adjusting one or more parameters of an operation performed by a drill controlling the drill bit based on the one or more drilling parameters output by the one or more machine learning models.   
     
     
         2 . The method of  claim 1 , wherein adjusting the one or more parameters of the operation performed by the drill comprises:
 adjusting parameters that control one or more of: drill steering, casing, or coring.   
     
     
         3 . The method of  claim 1 , wherein obtaining the sensor data from the at least one sensor attached to the surface of the drill bit comprises:
 obtaining the sensor data from (i) an acoustic sensor and (ii) a pressure sensor.   
     
     
         4 . The method of  claim 1 , wherein obtaining the sensor data from the at least one sensor attached to the surface of the drill bit comprises:
 obtaining the sensor data from an accelerometer.   
     
     
         5 . The method of  claim 1 , wherein providing the sensor data from the at least one sensor to the one or more machine learning models comprises:
 generating a transformed version of the sensor data; and   providing the transformed version of the sensor data to the one or more machine learning models.   
     
     
         6 . The method of  claim 5 , wherein generating the transformed version of the sensor data comprises:
 performing a fast Fourier transform (FFT) on the sensor data from the at least one sensor.   
     
     
         7 . The method of  claim 5 , wherein generating the transformed version of the sensor data comprises:
 extracting attributes from the sensor data; and   generating, using the extracted attributes, the transformed version of the sensor data.   
     
     
         8 . The method of  claim 7 , wherein the attributes include one or more of energy, amplitude, or phase. 
     
     
         9 . The method of  claim 1 , wherein adjusting the one or more parameters of the operation performed by the drill comprises:
 obtaining the output from the one or more machine learning models; and   adjusting, using one or more updated parameters included in the output from the one or more machine learning models, the one or more parameters of the operation performed by the drill.   
     
     
         10 . The method of  claim 1 , wherein obtaining the sensor data from the at least one sensor attached to the surface of the drill bit comprises:
 obtaining, during operation of the drill, the sensor data from the at least one sensor attached to the surface of the drill bit.   
     
     
         11 . The method of  claim 1 , wherein the one or more machine learning models are trained to predict one or more geological formations. 
     
     
         12 . The method of  claim 1 , comprising:
 generating the library of sensor signatures and geological formations as an electronic database using records from known geological formations.   
     
     
         13 . A system comprising one or more computers and one or more storage devices on which are stored instructions that are operable, when executed by the one or more computers, to cause the one or more computers to perform operations comprising:
 obtaining sensor data from at least one sensor attached to a surface of a drill bit;   providing the sensor data from the at least one sensor to one or more machine learning models, wherein the one or more machine learning models are trained using a library of (i) sensor signatures and (ii) geological formations to output one or more drilling parameters; and   adjusting one or more parameters of an operation performed by a drill controlling the drill bit based on the one or more drilling parameters output by the one or more machine learning models.   
     
     
         14 . The system of  claim 13 , wherein adjusting the one or more parameters of the operation performed by the drill comprises:
 adjusting parameters that control one or more of: drill steering, casing, or coring.   
     
     
         15 . The system of  claim 13 , wherein obtaining the sensor data from the at least one sensor attached to the surface of the drill bit comprises:
 obtaining the sensor data from (i) an acoustic sensor and (ii) a pressure sensor.   
     
     
         16 . The system of  claim 13 , wherein obtaining the sensor data from the at least one sensor attached to the surface of the drill bit comprises:
 obtaining the sensor data from an accelerometer.   
     
     
         17 . The system of  claim 13 , wherein providing the sensor data from the at least one sensor to the one or more machine learning models comprises:
 generating a transformed version of the sensor data; and   providing the transformed version of the sensor data to the one or more machine learning models.   
     
     
         18 . The system of  claim 17 , wherein generating the transformed version of the sensor data comprises:
 performing a fast Fourier transform (FFT) on the sensor data from the at least one sensor.   
     
     
         19 . The system of  claim 17 , wherein generating the transformed version of the sensor data comprises:
 extracting attributes from the sensor data; and   generating, using the extracted attributes, the transformed version of the sensor data.   
     
     
         20 . One or more computer storage media encoded with instructions that, when executed by one or more computers, cause the one or more computers to perform operations comprising:
 obtaining sensor data from at least one sensor attached to a surface of a drill bit;   providing the sensor data from the at least one sensor to one or more machine learning models, wherein the one or more machine learning models are trained using a library of (i) sensor signatures and (ii) geological formations to output one or more drilling parameters; and   adjusting one or more parameters of an operation performed by a drill controlling the drill bit based on the one or more drilling parameters output by the one or more machine learning models.