Automatic slips detection system for the optimization of real-time drilling operations
A method for determining a slips status during a drilling operation of a subterranean formation. The method includes capturing, using one or multiple camera devices mounted on a drilling rig of the drilling operation, a plurality of images, each of the plurality of images comprising a portion that corresponds to a slips device of the drilling rig, generating, using a sensor device of the drilling rig, a plurality of parameters of the drilling rig, wherein the plurality of parameters are synchronized with the plurality of images, providing, by a computer processor, the plurality of parameters as input to a machine learning model of the drilling rig, and analyzing, by the computer processor and based on the machine learning model, the plurality of images to generate the slips status.
1. A method for determining a slips status during a drilling operation of a subterranean formation, the method comprising:
capturing, using one or multiple camera devices mounted on a drilling rig of the drilling operation, a plurality of images, each of the plurality of images comprising a portion that corresponds to a slips device of the drilling rig;
generating, using a sensor device of the drilling rig, a plurality of parameters of the drilling rig, wherein the plurality of parameters are synchronized with the plurality of images;
providing, by a computer processor, the plurality of parameters as input to a machine learning model of the drilling rig; and
analyzing, by the computer processor and based on the machine learning model, the plurality of images to generate the slips status.
2. The method of claim 1 , further comprising:
generating, by the computer processor and based at least on the slips status, slips status statistics comprising one or more of an elapsed slips-to-slips time, an elapsed slips-to-weight time, an elapsed weight-to-slips time, and an elapsed weight-to-weight time.
3. The method of claim 2 , further comprising:
generating, by the computer processor and based at least on the slips status statistics, one or more of an alert and an actionable item; and
presenting, to a user, one or more of the slips status statistics, the alert, and the actionable item.
4. The method of claim 1 , further comprising:
performing, by the computer processor, the drilling operation based at least on the slips status.
5. The method of claim 1 , further comprising:
obtaining, in real-time and using one or more surface sensors of the drilling rig, the plurality of parameters of the drilling rig,
wherein the plurality of parameters of the drilling rig correspond to one or more of bit depth, hole depth, drilling mudflow, hook load, and rotary speed.
6. The method of claim 1 , further comprising:
obtaining, in a training phase, a plurality of training images, each of the plurality of training images comprising a labeled portion that corresponds to the slips device of the drilling rig; and
generating, using data augmentation techniques, a synthetic set of images to expand the plurality of images;
generating, based at least on the plurality of training images, the machine learning model.
7. The method of claim 1 ,
wherein generating the slips status, by analyzing the plurality of images based on the machine learning model, is performed in a testing phase subsequent to the training phase.
8. A computer system for determining a slips status during a drilling operation of a subterranean formation, comprising:
a processor; and
a memory coupled to the processor and storing instruction, the instructions, when executed by the processor, comprising functionality for:
capturing, using one or more camera devices mounted on a drilling rig of the drilling operation, a plurality of images, each of the plurality of images comprising a portion that corresponds to a slips device of the drilling rig;
generating, using a sensor device of the drilling rig, a plurality of parameters of the drilling rig, wherein the plurality of parameters are synchronized with the plurality of images;
providing the plurality of parameters as input to a machine learning model of the drilling rig; and
analyzing, based on the machine learning model, the plurality of images to generate the slips status.
9. The computer system of claim 8 , the instructions, when executed by the processor, further comprising functionality for:
generating, based at least on the slips status, slips status statistics comprising one or more of an elapsed slips-to-slips time, an elapsed slips-to-weight time, an elapsed weight-to-slips time, and an elapsed weight-to-weight time.
10. The computer system of claim 9 , the instructions, when executed by the processor, further comprising functionality for:
generating, based at least on the slips status statistics, one or more of an alert and an actionable item; and
presenting, to a user, one or more of the slips status statistics, the alert, and the actionable item.
11. The computer system of claim 8 , the instructions, when executed by the processor, further comprising functionality for:
performing the drilling operation based at least on the slips status.
12. The computer system of claim 8 , the instructions, when executed by the processor, further comprising functionality for:
obtaining, in real-time and using one or more surface sensors of the drilling rig, the plurality of parameters of the drilling rig,
wherein the plurality of parameters of the drilling rig correspond to one or more of bit depth, hole depth, drilling mudflow, hook load, and rotary speed.
13. The computer system of claim 8 , the instructions, when executed by the processor, further comprising functionality for:
obtaining, in a training phase, a plurality of training images, each of the plurality of training images comprising a labeled portion that corresponds to the slips device of the drilling rig;
generating, using data augmentation techniques, a synthetic set of images to expand the plurality of images; and
generating, based at least one the plurality of training images, the machine learning model.
14. The computer system of claim 8 ,
wherein generating the slips status, by analyzing the plurality of images based on the machine learning model, is performed in a testing phase subsequent to the training phase.
15. A non-transitory computer readable medium storing instructions executable by a computer processor for determining a slips status during a drilling operation of a subterranean formation, the instructions, when executed, comprising functionality for:
capturing, using one or more camera devices mounted on a drilling rig of the drilling operation, a plurality of images, each of the plurality of images comprising a portion that corresponds to a slips device of the drilling rig;
generating, using a sensor device of the drilling rig, a plurality of parameters of the drilling rig, wherein the plurality of parameters are synchronized with the plurality of images;
providing the plurality of parameters as input to a machine learning model of the drilling rig; and
analyzing, based on the machine learning model, the plurality of images to generate the slips status.
16. The non-transitory computer readable medium of claim 15 , the instructions, when executed, further comprising functionality for:
generating, based at least on the slips status, slips status statistics comprising one or more of an elapsed slips-to-slips time, an elapsed slips-to-weight time, an elapsed weight-to-slips time, and an elapsed weight-to-weight time.
17. The non-transitory computer readable medium of claim 16 , the instructions, when executed, further comprising functionality for:
generating, by the computer processor and based at least on the slips status statistics, one or more of an alert and an actionable item; and
presenting, to a user, one or more of the slips status statistics, the alert, and the actionable item.
18. The non-transitory computer readable medium of claim 15 , the instructions, when executed, further comprising functionality for:
performing the drilling operation based at least on the slips status.
19. The non-transitory computer readable medium of claim 15 , the instructions, when executed, further comprising functionality for:
obtaining, in real-time and using one or more surface sensors of the drilling rig, the plurality of parameters of the drilling rig,
wherein the plurality of parameters of the drilling rig correspond to one or more of bit depth, hole depth, drilling mudflow, hook load, and rotary speed.
20. The non-transitory computer readable medium of claim 15 , the instructions, when executed, further comprising functionality for:
obtaining, in a training phase, a plurality of training images, each of the plurality of training images comprising a labeled portion that corresponds to the slips device of the drilling rig;
generating, using data augmentation techniques, a synthetic set of images to expand the plurality of images; and
generating, based at least one the plurality of training images, the machine learning model,
wherein generating the slips status, by analyzing the plurality of images based on the machine learning model, is performed in a testing phase subsequent to the training phase.