Connection analyzed make-up systems and methods

1. A method, comprising:

acquiring measurements representing torque applied to a connection between a first tubular and a second tubular, a rotational position of the first tubular relative to the second tubular, or both;

obtaining a plurality of make-up parameters representing conditions under which the connection is fully made;

generating a plurality of rules for connection evaluation based on the make-up parameters;

automatically evaluating the connection using a computer, wherein automatically evaluating the connection comprises applying a plurality of static rules to determine connection acceptability, and applying a machine learning to optimize connection makeup or determine whether an anomaly has occurred while making the connection; and

recommending accepting or rejecting the connection based on the automatic evaluation.

2. The method of claim 1 , wherein the automatic evaluating occurs while the connection is being made, before the connection is complete.

3. The method of claim 1 , wherein automatically evaluating further comprises determining a probability value of an acceptable connection or an unacceptable connection prior to the connection being formed.

4. The method of claim 1 , wherein automatically evaluating comprises using the machine learning trained using a training corpus of connection torque-turn plots.

5. The method of claim 4 , wherein automatically evaluating the connection comprises:

determining probabilities of a plurality of individual anomalies present in the dataset as an output of the machine learning; and

classifying the output of the machine learning to identify an anomaly present in the dataset.

6. The method of claim 4 , further comprising:

acquiring the training corpus of datasets acquired during historical connection processes, wherein the datasets are each associated with at least one of acceptance, rejection, or a specific anomaly in the respective, associated historical connection processes; and

training the machine learning using the training corpus.

7. The method of claim 4 , further comprising extracting a subset of the acquired measurements, wherein the dataset comprises the extracted subset and not a remainder of the measurements that were not extracted.

8. The method of claim 7 , wherein extracting comprises applying a filter, a moving window, or a combination thereof to the measurements.

9. The method of claim 4 , wherein the machine learning comprises a first machine learning configured to determine whether the dataset indicates a connection should be accepted or rejected, and a second machine learning configured to identify particular anomalies in the dataset.

10. The method of claim 4 , wherein the automatic evaluating occurs while the connection is being made, and wherein the method further comprises indicating a detected anomaly based on the automatic evaluating prior to a completion of the connection.

11. The method of claim 4 , wherein the automatic evaluating occurs while the connection is being made, the method further comprising:

determining an anomaly is present in the dataset before the connection is completed, or that an anomaly is likely in the future of the connection based on the dataset;

determining that a corrective action is available; and

adjusting an operating parameter of a tubular rotating component to avoid or mitigate a consequence of the determined anomaly or the anomaly that is likely in the future.

12. The method of claim 11 , wherein adjusting the operating parameter comprises adjusting a speed or a torque of the tubular rotating component.

13. The method of claim 11 , wherein determining that the corrective action is available comprises forecasting an effect of adjusting the operating parameter of the tubular rotating component using the machine learning.

14. The method of claim 1 , wherein evaluating comprises identifying a particular anomaly based on the plurality of rules, and wherein the anomaly is selected from the group consisting of: Overtorque, Undertorque, High Shoulder, Low Shoulder, High Delta Turns, Low Delta Turns, High Delta Slope, Low Delta Slope, Dope Squeeze, Slippage, High Interference, Not Enough Turns, No Shoulder, Cross Threading, and Damaged Dump Valve.

15. The method of claim 1 , wherein the make-up parameters include at least one parameter selected from the group consisting of: Make/Break mode, Shoulder Detect on/off, Makeup Type, Delta Torque, Delta Turns, Maximum Torque, Optimum Torque, Minimum Torque, Maximum Shoulder Torque, Minimum Shoulder Torque, Connection Delta Turn Minimum, Connection Delta Turn Maximum, Connection Delta Slope Minimum, Connection Delta Slope Maximum, Datapoints comprising Turns, Torque, RPM, and Time, Shoulder Point, and Double Bumped on/off.

16. A system, comprising:

a tubular rotating component configured to make a connection between a first tubular and a second tubular by rotating the first tubular, wherein the tubular rotating component comprises one or more sensors configured to measure torque applied to the first and/or second tubular, a rotational position of the first tubular relative to the second tubular, or both;

a controller in communication with the one or more sensors; and

one or more non-transitory, computer-readable media storing instructions thereon that, when executed by a processor of the controller, cause the controller to perform operations, the operations comprising:

acquiring, from the one or more sensors, measurements representing torque applied to a connection between the first tubular and the second tubular, a rotational position of the first tubular relative to the second tubular, or both;

obtaining a plurality of make-up parameters representing conditions under which the connection is fully made;

generating a plurality of rules for connection evaluation based on the make-up parameters;

automatically evaluating the connection, wherein automatically evaluating the connection comprises applying a plurality of static rules to determine connection acceptability, and applying a machine learning to optimize connection makeup or determine whether an anomaly has occurred while making the connection; and

recommending accepting or rejecting the connection based on the automatic evaluation.

17. The system of claim 16 , wherein the automatic evaluating occurs while the connection is being made, before the connection is complete.

18. The system of claim 16 , wherein automatically evaluating further comprises determining a probability value of an acceptable connection or an unacceptable connection.

19. The system of claim 16 , wherein automatically evaluating comprises:

acquiring a training corpus of datasets acquired during historical connection processes, wherein the datasets are each associated with at least one of acceptance, rejection, or a specific anomaly in the respective, associated historical connection processes;

training the machine learning using the training corpus;

determining probabilities of a plurality of individual anomalies present in the dataset as an output of the machine learning; and

classifying the output of the machine learning to identify an anomaly present in the dataset.

20. The system of claim 19 , further comprising extracting a subset of the acquired measurements, wherein the dataset comprises the extracted subset and not a remainder of the measurements that were not extracted, wherein extracting comprises applying a filter, a moving window, or a combination thereof to the measurements.

21. The system of claim 19 , wherein the machine learning comprises a first machine learning configured to determine whether the dataset indicates a connection should be accepted or rejected, and a second machine learning configured to identify particular anomalies in the dataset.