Well construction equipment framework
A method can include receiving input for a drilling operation that utilizes a bottom hole assembly and drilling fluid; generating a set of offset drilling operations using historical feature data, where the historical feature data are processed by computing feature distances; performing an assessment of the offset drilling operations as characterized by at least feature distance-based similarity between the drilling operation and the offset drilling operations; and outputting at least one recommendation for selection of one or more of a component of the bottom hole assembly and the drilling fluid based on the assessment.
1. A method comprising:
receiving input for a drilling operation that utilizes a bottom hole assembly and drilling fluid;
generating a set of offset drilling operations using historical feature data and predicted feature data from one or more machine learning models based on at least a portion of the input, wherein the historical feature data is processed by computing feature distances;
performing an assessment of the set of offset drilling operations as characterized by feature distance-based similarity between the drilling operation and the set of offset drilling operations, wherein the feature distance-based similarity is determined by:
receiving a first selection of one or more pair-wise distance metrics of a set of data points within a multidimensional space plot via a graphical user interface (GUI), wherein each of the one or more pair-wise distance metrics corresponds to the drilling operation and one of the set of offset drilling operations;
receiving one or more weights associated with the one or more pair-wise distance metrics via the GUI;
generating one or more weighted pair-wise distance metrics based on the one or more pair-wise distance metrics and the one or more weights;
determining a similarity index for each of the one or more weights associated with the one or more pair-wise distance metrics; and
generating, based on the similarity index, at least one recommendation of an adjustment to a trajectory of the drilling operation by the bottom hole assembly and a flow of the drilling fluid;
outputting the at least one recommendation for selection via the GUI;
receiving at least one rating as feedback, via the GUI, to the at least one recommendation and training at least one of the one or more machine learning models based at least in part on the at least one rating;
receiving the selection of the at least one recommendation via the GUI; and
sending one or more commands to the bottom hole assembly in response to receiving the selection, wherein the one or more commands are configured to cause the bottom hole assembly to adjust the trajectory of the drilling operation or the flow of the drilling fluid according to the selection.
2. The method of claim 1 , wherein the feature distances correspond to one or more pairs of individual offset drilling operations within the historical feature data.
3. The method of claim 1 , wherein generating the set comprises performing clustering that generates clusters.
4. The method of claim 3 , wherein generating the set of offset drilling operations comprises performing classifying using the clusters and using information associated with the drilling operation.
5. The method of claim 1 , wherein generating the set of offset drilling operations comprises utilizing multiple machine learning models that comprise at least a machine learning model trained using unsupervised learning and a machine learning model trained using supervised learning.
6. The method of claim 1 , wherein performing the assessment comprises filtering using one or more filter criteria.
7. The method of claim 6 , wherein the one or more filter criteria comprise at least content based filtering.
8. The method of claim 1 , wherein performing the assessment comprises receiving a similarity index threshold value that splits the set of offset drilling operations into a more similar portion and a less similar portion with respect to the drilling operation.
9. The method of claim 1 , wherein the feature distances comprise multidimensional feature distances that correspond to pairs of individual offset drilling operations in the historical feature data.
10. The method of claim 1 , wherein performing the assessment comprises receiving additional input responsive to interaction with the graphical user interface rendered to a display.
11. The method of claim 10 , wherein the additional input comprises one or more scoring weight values.
12. The method of claim 1 , wherein performing the assessment comprises ranking at least a portion of the set of offset drilling operations.
13. The method of claim 1 , wherein the at least one recommendation comprises feature results that comprise at least one feature result for each of a plurality of features.
14. The method of claim 13 , wherein each of the feature results for a corresponding one of the plurality of features is generated using a corresponding trained machine learning model.
15. The method of claim 13 , comprising generating graphics that represent probabilities for the features results, wherein the graphics represent probabilities for predicted features and a type of trained machine learning model utilized to generate each of the predicted features.
16. The method of claim 1 , comprising generating a map with graphics that represent the set of offset drilling operations based on one or more feature distance-based similarity metrics.
17. The method of claim 1 , wherein the at least one recommendation comprises a recommended component of the bottom hole assembly and a recommended drilling fluid for the drilling operation.
18. A system comprising:
a processor;
memory accessible to the processor;
processor-executable instructions stored in the memory and executable by the processor to instruct the system to:
receive input for a drilling operation that utilizes a bottom hole assembly and drilling fluid;
generate a set of offset drilling operations using historical feature data and predicted feature data from one or more machine learning models based on at least a portion of the input, wherein the historical feature data is processed by computing feature distances;
perform an assessment of the set of offset drilling operations as characterized by feature distance-based similarity between the drilling operation and the set of offset drilling operations, wherein the feature distance-based similarity is determined by:
receiving a first selection of one or more pair-wise distance metrics of a set of data points within a multidimensional space plot via a graphical user interface (GUI), wherein each of the one or more pair-wise distance metrics corresponds to the drilling operation and one of the set of offset drilling operations;
receiving one or more weights associated with the one or more pair-wise distance metrics via the GUI;
generating one or more weighted pair-wise distance metrics based on the one or more pair-wise distance metrics and the one or more weights;
determining a similarity index for each of the one or more weights associated with the one or more pair-wise distance metrics; and
generating, based on the similarity index, at least one recommendation of an adjustment to a trajectory of the drilling operation by the bottom hole assembly and a flow of the drilling fluid;
output the at least one recommendation for selection via the GUI;
receive at least one rating as feedback, via the GUL to the at least one recommendation and training at least one of the one or more machine learning models based at least in part on the at least one rating;
receive the selection of the at least one recommendation via the GUI; and
send one or more commands to the bottom hole assembly in response to receiving the selection, wherein the one or more commands are configured to cause the bottom hole assembly to adjust the trajectory of the drilling operation or the flow of the drilling fluid according to the selection.
19. One or more non-transitory computer-readable storage media comprising computer-executable instructions executable to instruct a computing system to:
receive input for a drilling operation that utilizes a bottom hole assembly and drilling fluid;
generate a set of offset drilling operations using historical feature data and predicted feature data from one or more machine learning models based on at least a portion of the input, wherein the historical feature data is processed by computing feature distances;
perform an assessment of the offset drilling operations as characterized by at least feature distance-based similarity between the drilling operation and the offset drilling operations, wherein the feature distance-based similarity is determined by:
receiving a first selection of one or more pair-wise distance metrics of a set of data points within a multidimensional space plot via a graphical user interface (GUI), wherein each of the one or more pair-wise distance metrics corresponds to the drilling operation and one of the set of offset drilling operations;
receiving one or more weights associated with the one or more pair-wise distance metrics via the GUI;
generating one or more weighted pair-wise distance metrics based on the one or more pair-wise distance metrics and the one or more weights;
determining a similarity index for each of the one or more weights associated with the one or more pair-wise distance metrics; and
generating, based on the similarity index, at least one recommendation of an adjustment to a trajectory of the drilling operation by the bottom hole assembly and a flow of the drilling fluid;
output the at least one recommendation for selection via the GUI;
receive at least one rating as feedback, via the GUI, to the at least one recommendation and training at least one of the one or more machine learning models based at least in part on the at least one rating;
receive the selection of the at least one recommendation via the GUI; and
send one or more commands to the bottom hole assembly in response to receiving the selection, wherein the one or more commands are configured to cause the bottom hole assembly to adjust the trajectory of the drilling operation or the flow of the drilling fluid according to the selection.