OPTIMIZATION OF RATE-OF-PENETRATION

1 . A method comprising:

receiving sensor data characterizing one or more properties of a first formation undergoing drilling;

determining, based on the received sensor data and a plurality of clustered historical data, an identity of the first formation;

determining, based on one or more of the identity of the first formation and a target rate of penetration, a target operating parameter of a drill configured to penetrate the first formation, the target operating parameter configured to achieve the target rate of penetration of the drill through the first formation; and

varying the operation of the drill based on the target operating parameter.

2 . The method of claim 1 , further comprising generating clustered historical data, the generating comprising:

receiving historical sensor data indicative of detected properties of a plurality of formations including the first formation;

encoding the historical sensor data into encoded data;

clustering the encoded data into a plurality of clustered encoded data indicative of the plurality of formations; and

clustering the historical sensor data into a plurality of clustered historical data based on the plurality of clustered encoded data, the plurality of clustered historical data indicative of the plurality of formations.

3 . The method of claim 2 , wherein clustering the encoded data into the plurality of clustered encoded data includes applying an unsupervised clustering algorithm on the encoded data, the unsupervised clustering algorithm configured to:

identify a first formation property in the encoded data; and

cluster the encoded data based on the first formation property.

4 . The method of claim 2 , wherein determining the identity of the first formation includes:

identifying a first clustered historical data of the plurality of clustered historical data representative of the received sensor data; and

setting the identity of the first formation to a formation associated with the first clustered historical data.

5 . The method of claim 4 , further comprising generating a predictive model for the first formation based at least on the first clustered historical data, wherein the predictive model is configured to determine the target operating parameter based on the identity of the first formation and the target rate of penetration.

6 . The method of claim 5 , wherein generating the predictive model includes:

determining one or more coefficients of a characteristic equation, the characteristic equation configured to receive a value representative of the first formation and the target rate of penetration as an input and generate the target operating parameter as an output.

7 . The method of claim 5 , wherein the predictive model is one of a Bayesian hybrid model and a Gaussian process based model.

8 . The method of claim 5 , wherein the predictive model is generated by a global evolutionary algorithm.

9 . A system comprising:

at least one data processor;

memory coupled to the at least one data processor, the memory storing instructions to cause the at least one data processor to perform operations comprising:

receiving sensor data characterizing one or more properties of a first formation undergoing drilling;

determining, based on the received sensor data and a plurality of clustered historical data, an identity of the first formation;

determining, based on one or more of the identity of the first formation and a target rate of penetration, a target operating parameter of a drill configured to penetrate the first formation, the target operating parameter configured to achieve the target rate of penetration of the drill through the first formation; and

varying the operation of the drill based on the target operating parameter.

10 . The system of claim 9 , wherein the operations further include generating clustered historical data, the generating comprising:

receiving historical sensor data indicative of detected properties of a plurality of formations including the first formation;

encoding the historical sensor data into encoded data;

clustering the encoded data into a plurality of clustered encoded data indicative of the plurality of formations; and

clustering the historical sensor data into a plurality of clustered historical data based on the plurality of clustered encoded data, the plurality of clustered historical data indicative of the plurality of formations.

11 . The system of claim 10 , wherein clustering the encoded data into the plurality of clustered encoded data includes applying an unsupervised clustering algorithm on the encoded data, the unsupervised clustering algorithm configured to:

identify a first formation property in the encoded data; and

cluster the encoded data based on the first formation property.

12 . The system of claim 10 , wherein determining the identity of the first formation includes:

identifying a first clustered historical data of the plurality of clustered historical data representative of the received sensor data; and

setting the identity of the first formation to a formation associated with the first clustered historical data.

13 . The system of claim 12 , wherein the operations further include generating a predictive model for the first formation based at least on the first clustered historical data, wherein the predictive model is configured to determine the target operating parameter based on the identity of the first formation and the target rate of penetration.

14 . The system of claim 13 , wherein generating the predictive model includes:

determining one or more coefficients of a characteristic equation, the characteristic equation configured to receive a value representative of the first formation and the target rate of penetration as an input and generate the target operating parameter as an output.

15 . The system of claim 13 , wherein the predictive model is one of a Bayesian hybrid model and a Gaussian process based model.

16 . The system of claim 13 , wherein the predictive model is generated by a global evolutionary algorithm.

17 . A computer program product comprising a non-transitory machine-readable medium storing instructions that, when executed by at least one programmable processor that comprises at least one physical core and a plurality of logical cores, cause the at least one programmable processor to perform operations comprising:

receiving sensor data characterizing one or more properties of a first formation undergoing drilling;

determining, based on the received sensor data and a plurality of clustered historical data, an identity of the first formation;

determining, based on one or more of the identity of the first formation and a target rate of penetration, a target operating parameter of a drill configured to penetrate the first formation, the target operating parameter configured to achieve the target rate of penetration of the drill through the first formation; and

varying the operation of the drill based on the target operating parameter.

18 . The computer program product of claim 17 , wherein the operations further include generating clustered historical data, the generating comprising:

receiving historical sensor data indicative of detected properties of a plurality of formations including the first formation;

encoding the historical sensor data into encoded data;

clustering the encoded data into a plurality of clustered encoded data indicative of the plurality of formations; and

clustering the historical sensor data into a plurality of clustered historical data based on the plurality of clustered encoded data, the plurality of clustered historical data indicative of the plurality of formations.

19 . The computer program product of claim 18 , wherein clustering the encoded data into the plurality of clustered encoded data includes applying an unsupervised clustering algorithm on the encoded data, the unsupervised clustering algorithm configured to:

identify a first formation property in the encoded data; and

cluster the encoded data based on the first formation property.

20 . The computer program product of claim 18 , wherein determining the identity of the first formation includes:

identifying a first clustered historical data of the plurality of clustered historical data representative of the received sensor data; and

setting the identity of the first formation to a formation associated with the first clustered historical data.