Parameter inference, depth estimation, and anomaly detection for coiled tubing operation automation

Abstract

Systems and methods presented herein facilitate coiled tubing operations, and generally relate to the use of mechanical models for the automation of such coiled tubing operations in the oil and gas industry. In particular, a framework is presented that includes three main building blocks: (1) a probabilistic tubing force and depth estimation package; (2) an anomaly detection package; and (3) a mechanical failure check package, each of which are software packages executable by a surface processing system.

1 . A method, comprising:
 executing, via a processing system, an inference model to automatically infer one or more observable system states and/or one or more uncertain system states relating to running a downhole well tool into a wellbore via coiled tubing during a coiled tubing operation;   executing, via the processing system, a tubing force calculation model to automatically calculate a tubing force profile along the coiled tubing based at least in part on the one or more observable system states and/or the one or more uncertain system states; and   executing, via the processing system, a surface weight uncertainty quantification model to automatically calculate a surface weight of the downhole well tool and the coiled tubing and uncertainty bounds around the calculated surface weight based at least in part on the one or more observable system states and/or the one or more uncertain system states and the calculated tubing force profile, wherein the surface weight uncertainty quantification model accounts for one or more uncertainties related to the one or more uncertain system states.   
     
     
         2 . The method of  claim 1 , comprising automatically adjusting, via the processing system, one or more operational parameters of the coiled tubing operation based at least in part on the calculated surface weight. 
     
     
         3 . The method of  claim 1 , wherein the one or more observable system states comprise a depth of the downhole well tool, a speed of the downhole well tool moving through the wellbore, or some combination thereof. 
     
     
         4 . The method of  claim 1 , wherein the one or more uncertain system states comprise a friction coefficient, a stripper friction, or some combination thereof. 
     
     
         5 . The method of  claim 1 , wherein executing, via the processing system, the inference model comprises using Bayes filtering. 
     
     
         6 . The method of  claim 1 , wherein executing, via the processing system, the inference model comprises using optimization-based analyses. 
     
     
         7 . The method of  claim 1 , comprising executing, via the processing system, a mechanical failure model to automatically monitor a mechanical safety of the coiled tubing based at least in part on the calculated tubing force profile along the coiled tubing. 
     
     
         8 . The method of  claim 1 , comprising executing, via the processing system, an anomaly detection model to automatically detect downhole anomalies relating to the downhole well tool based at least in part on the calculated surface weight of the downhole well tool and the coiled tubing and the uncertainty bounds around the calculated surface weight. 
     
     
         9 . A tangible non-transitory computer-readable media comprising process-executable instructions that, when executed by one or more processors, cause the one or more processors to:
 execute an inference model to automatically infer one or more observable system states and/or one or more uncertain system states relating to running a downhole well tool into a wellbore via coiled tubing during a coiled tubing operation;   execute a tubing force calculation model to automatically calculate a tubing force profile along the coiled tubing based at least in part on the one or more observable system states and/or the one or more uncertain system states; and   execute a surface weight uncertainty quantification model to automatically calculate a surface weight of the downhole well tool and the coiled tubing and uncertainty bounds around the calculated surface weight based at least in part on the one or more observable system states and/or the one or more uncertain system states and the calculated tubing force profile, wherein the surface weight uncertainty quantification model accounts for one or more uncertainties related to the one or more uncertain system states.   
     
     
         10 . The tangible non-transitory computer-readable media of  claim 9 , wherein the process-executable instructions, when executed by one or more processors, cause the one or more processors to adjust one or more operational parameters of the coiled tubing operation based at least in part on the calculated surface weight. 
     
     
         11 . The tangible non-transitory computer-readable media of  claim 9 , wherein the one or more observable system states comprise a depth of the downhole well tool, a speed of the downhole well tool moving through the wellbore, or some combination thereof. 
     
     
         12 . The tangible non-transitory computer-readable media of  claim 9 , wherein the one or more uncertain system states comprise a friction coefficient, a stripper friction, or some combination thereof. 
     
     
         13 . The tangible non-transitory computer-readable media of  claim 9 , wherein the process-executable instructions, when executed by one or more processors, cause the one or more processors to execute the inference model using Bayes filtering. 
     
     
         14 . The tangible non-transitory computer-readable media of  claim 9 , wherein the process-executable instructions, when executed by one or more processors, cause the one or more processors to execute the inference model using optimization-based analyses. 
     
     
         15 . The tangible non-transitory computer-readable media of  claim 9 , wherein the process-executable instructions, when executed by one or more processors, cause the one or more processors to execute a mechanical failure model to automatically monitor a mechanical safety of the coiled tubing based at least in part on the calculated tubing force profile along the coiled tubing. 
     
     
         16 . The tangible non-transitory computer-readable media of  claim 9 , wherein the process-executable instructions, when executed by one or more processors, cause the one or more processors to execute an anomaly detection model to automatically detect downhole anomalies relating to the downhole well tool based at least in part on the calculated surface weight of the downhole well tool and the coiled tubing and the uncertainty bounds around the calculated surface weight. 
     
     
         17 . A system, comprising:
 a surface processing system configured to:
 execute an inference model to automatically infer one or more observable system states and/or one or more uncertain system states relating to running a downhole well tool into a wellbore via coiled tubing during a coiled tubing operation; 
 execute a tubing force calculation model to automatically calculate a tubing force profile along the coiled tubing based at least in part on the one or more observable system states and/or the one or more uncertain system states; and 
 execute a surface weight uncertainty quantification model to automatically calculate a surface weight of the downhole well tool and the coiled tubing and uncertainty bounds around the calculated surface weight based at least in part on the one or more observable system states and/or the one or more uncertain system states and the calculated tubing force profile, wherein the surface weight uncertainty quantification model accounts for one or more uncertainties related to the one or more uncertain system states. 
   
     
     
         18 . The system of  claim 17 , wherein the surface processing system is configured to adjust one or more operational parameters of the coiled tubing operation based at least in part on the calculated surface weight. 
     
     
         19 . The system of  claim 17 , wherein the surface processing system is configured to execute a mechanical failure model to automatically monitor a mechanical safety of the coiled tubing based at least in part on the calculated tubing force profile along the coiled tubing. 
     
     
         20 . The system of  claim 17 , wherein the surface processing system is configured to execute an anomaly detection model to automatically detect downhole anomalies relating to the downhole well tool based at least in part on the calculated surface weight of the downhole well tool and the coiled tubing and the uncertainty bounds around the calculated surface weight.