Parameter inference, depth estimation, and anomaly detection for conveyance automation

Abstract

Processes and systems for automating a conveyance operation using an elongated conveyance member. In some embodiments, the process can include modeling one or more system state profiles of a downhole tool string during the conveyance operation within a wellbore to define one or more profile models; calibrating the one or more profile models; using the one or more calibrated profile models to calculate at least one of a tension profile and a force profile along the elongated conveyance member based, at least in part, on one or more detectable system states and/or one or more undetectable system states; and using one of: (i) a surface tension uncertainty quantification model to calculate a surface tension and uncertainty bounds around the calculated surface tension; or (ii) a surface weight uncertainty quantification model to calculate a surface weight and uncertainty bounds around the calculated surface weight.

What is claimed is: 
     
         1 . A process for automating a conveyance operation using an elongated conveyance member, comprising:
 modeling one or more system state profiles of a downhole tool string during a conveyance operation within a wellbore to define one or more profile models;   calibrating the one or more profile models using one or more inference models by inferring one or more detectable system states and/or one or more undetectable system states related to running the downhole tool string into the wellbore via the elongated conveyance member to determine one or more calibrated profile models;   using the one or more calibrated profile models to calculate at least one of a tension profile and a force profile along the elongated conveyance member based, at least in part, on the one or more detectable system states and/or the one or more undetectable system states; and   using one of:
 (i) a surface tension uncertainty quantification model to calculate a surface tension and uncertainty bounds around the calculated surface tension based, at least in part, on the one or more detectable system states and/or the one or more undetectable system states, and the calculated tension profile, wherein the surface tension uncertainty quantification model accounts for one or more uncertainties related to the one or more detectable system states and/or the one or more undetectable system states; or 
 (ii) a surface weight uncertainty quantification model to calculate a surface weight and uncertainty bounds around the calculated surface weight based, at least in part, on the one or more detectable system states and/or the one or more undetectable system states, and the calculated force profile, wherein the surface weight uncertainty quantification model accounts for one or more uncertainties related to the one or undetectable system states. 
   
     
     
         2 . The process of  claim 1 , wherein the elongated conveyance member is a wireline, a slickline, or a coiled tubing. 
     
     
         3 . The process of  claim 1 , wherein the elongated conveyance member is a wireline or a slickline and the one or more system state profiles comprise a speed profile, a tension profile, and a depth profile. 
     
     
         4 . The process of  claim 1 , wherein the one or more system state profiles comprise at least one of a tension profile and a force profile. 
     
     
         5 . The process of  claim 1 , wherein the one or more detectable system states comprise a depth of the downhole tool string within the wellbore, a speed of the downhole tool string within the wellbore, or a combination thereof. 
     
     
         6 . The process of  claim 1 , wherein the one or more undetectable system states comprise a friction coefficient between the downhole tool string and the wellbore, a stripper friction, a fluid level, a wellbore fluid density, or a combination thereof. 
     
     
         7 . The process of  claim 1 , wherein using the one or more inference models to infer the one or more detectable system states and/or the one or more undetectable system states comprises using Bayes filtering. 
     
     
         8 . The process of  claim 1 , wherein using the one or more inference models to infer the one or more detectable system states and/or the one or more undetectable system states comprises using optimization-based analyses. 
     
     
         9 . The process of  claim 1 , further comprising using a mechanical failure model to automatically monitor a mechanical safety of the elongated conveyance member based, at least in part, on one of the calculated tension profile or the calculated force profile along the elongated conveyance member based. 
     
     
         10 . The process of  claim 1 , further comprising using an anomaly detection model to automatically detect downhole anomalies relating to the downhole tool string based, at least in part, on at least one of the calculated surface tension and the uncertainty bounds around the calculated surface tension, and the calculated surface weight and uncertainty bounds around the calculated surface weight. 
     
     
         11 . A system comprising:
 a network adapter configured to acquire sensor data from sensors during a conveyance operation within a wellbore using an elongated conveyance member; and   at least one processor configured to execute an executable code to implement at least the functionality of modeling one or more system state profiles of a downhole tool string during the conveyance operation to define one or more profile models, wherein the at least one processor is further configured to:
 calibrate the one or more profile models using one or more inference models by inferring one or more detectable system states and/or one or more undetectable system states related to running the downhole tool string into the wellbore via the elongated conveyance member to determine one or more calibrated profile models; 
 use the one or more calibrated profile models to calculate at least one of a tension profile and a force profile along the elongated conveyance member based, at least in part, on the one or more detectable system states and/or the one or more undetectable system states; and 
 use one of:
 (i) a surface tension uncertainty quantification model to calculate a surface tension and uncertainty bounds around the calculated surface tension based, at least in part, on the one or more detectable system states and/or the one or more undetectable system states, and the calculated tension profile, wherein the surface tension uncertainty quantification model accounts for one or more uncertainties related to the one or more detectable system states and/or one or more undetectable system states; or 
 (ii) a surface weight uncertainty quantification model to calculate a surface weight and uncertainty bounds around the calculated surface weight based, at least in part, on the one or more detectable system states and/or the one or more undetectable system states, and the calculated force profile, wherein the surface weight uncertainty quantification model accounts for one or more uncertainties related to the one or undetectable system states. 
 
   
     
     
         12 . The system of  claim 11 , wherein the at least one processor is configured to execute the executable code to use Bayes filtering to infer the one or more detectable system states and/or the one or more undetectable system states using the one or more inference models. 
     
     
         13 . The system of  claim 11 , wherein the at least one processor is configured to execute the executable code to use optimization-based analyses to infer the one or more detectable system states and/or the one or more undetectable system states using the one or more inference models. 
     
     
         14 . The system of  claim 11 , further comprising executable code configured to be executed by the at least one processor to use a mechanical failure model to automatically monitor a mechanical safety of the elongated conveyance member based, at least in part, on the calculated tension profile along the elongated conveyance member. 
     
     
         15 . The system of  claim 11 , further comprising executable code configured to be executed by the at least one processor to use an anomaly detection model to automatically detect downhole anomalies relating to the downhole tool string based, at least in part, on the calculated surface tension and the uncertainty bounds around the calculated surface tension. 
     
     
         16 . A system comprising:
 at least one processor configured to execute an executable code to implement at least the functionality of modeling one or more system state profiles of a downhole tool string during a conveyance operation via an elongated conveyance member within a wellbore to define one or more profile models, wherein the at least one processor is further configured to:
 calibrate the one or more profile models using one or more inference models by inferring one or more detectable system states and/or one or more undetectable system states related to running the downhole tool string into the wellbore via the elongated conveyance member to determine one or more calibrated profile models; 
   use the one or more calibrated profile models to calculate at least one of a tension profile and a force profile along the elongated conveyance member based, at least in part, on the one or more detectable system states and/or the one or more undetectable system states; and   use one of:
 (i) a surface tension uncertainty quantification model to calculate a surface tension and uncertainty bounds around the calculated surface tension based, at least in part, on the one or more detectable system states and/or the one or more undetectable system states, and the calculated tension profile, wherein the surface tension uncertainty quantification model accounts for one or more uncertainties related to the one or more detectable system states and/or one or more undetectable system states; or 
 (ii) a surface weight uncertainty quantification model to calculate a surface weight and uncertainty bounds around the calculated surface weight based, at least in part, on the one or more detectable system states and/or the one or more undetectable system states, and the calculated force profile, wherein the surface weight uncertainty quantification model accounts for one or more uncertainties related to the one or undetectable system states. 
   
     
     
         17 . The system of  claim 16 , wherein the at least one processor is configured to execute the executable code to use Bayes filtering to infer the one or more detectable system states and/or the one or more undetectable system states using the one or more inference models. 
     
     
         18 . The system of  claim 16 , wherein the at least one processor is configured to execute the executable code to use optimization-based analyses to infer the one or more detectable system states and/or the one or more undetectable system states using the one or more inference models. 
     
     
         19 . The system of  claim 16 , further comprising executable code configured to be executed by the at least one processor to use a mechanical failure model to automatically monitor a mechanical safety of the elongated conveyance member based, at least in part, on the calculated tension profile along the along the elongated conveyance member. 
     
     
         20 . The system of  claim 16 , further comprising executable code configured to be executed by the at least one processor to use an anomaly detection model to automatically detect downhole anomalies relating to the downhole tool string based, at least in part, on the calculated surface tension and the uncertainty bounds around the calculated surface tension.