Methods for improving performance of automated coiled tubing operations

Abstract

Systems and methods presented herein facilitate coiled tubing operations, and generally relate to the use of flow modeling to generate flow-related data that cannot be measured in order to take re-al-time decisions and real-time predictions on the outcome of future potential actions to be taken by engineers or artificial intelligence to optimize operation performance together with a general method for parameter inference for any uncertain parameters deemed important when designing cleanout operations. In certain situations, a pre-conditioning method for the determination of a reservoir pressure parameter may be used to reduce the effect of its uncertainty on design fidelity. In addition, in certain situations, a pre-conditioning method for the determination of a reservoir inflow performance parameter may be used to reduce the effect of its uncertainty on design fidelity.

1 . A method, comprising:
 (a) accessing, via a processing system, a real-time pumping schedule for a pump unit configured to pump one or more fluids downhole into a wellbore via coiled tubing, wherein the real-time pumping schedule specifies one or more operational parameters relating to pumping of the one or more fluids downhole into the wellbore via the coiled tubing;   (b) executing, via the processing system, a forward model to predict values of one or more measurable input parameters relating to pumping of the one or more fluids;   (c) accessing, via the processing system, current measurements of the one or more measurable input parameters detected by one or more sensors;   (d) executing, via the processing system, an inverse model to predict one or more unmeasurable input parameters relating to pumping of the one or more fluids based on a comparison of the predicted values of the one or more measurable input parameters and the current measurements of the one or more measurable input parameters; and   (e) estimating, via the processing system, one or more additional unmeasurable input parameters based at least in part on the one or more measurable input parameters and the one or more unmeasurable input parameters.   
     
     
         2 . The method of  claim 1 , wherein the one or more operational parameters specified by the real-time pumping schedule comprise types of the one or more fluids, flow rates of the one or more fluids, pressures in the wellbore as a function of depth along the wellbore, a speed of movement of the coiled tubing through the wellbore, or some combination thereof. 
     
     
         3 . The method of  claim 1 , wherein the one or more measurable input parameters comprise the one or more operational parameters specified by the real-time pumping schedule. 
     
     
         4 . The method of  claim 1 , wherein the forward model uses one or more static parameters and one or more dynamic parameters as inputs. 
     
     
         5 . The method of  claim 4 , wherein the one or more static parameters comprise a hole survey of the wellbore, geometry of the wellbore, completion diagram of the wellbore, one or more properties of the one or more fluids, one or more properties of the coiled tubing, and one or more properties of a reservoir. 
     
     
         6 . The method of  claim 4 , wherein the one or more dynamic parameters comprise current measurements of the one or more measurable input parameters. 
     
     
         7 . The method of  claim 4 , wherein the inverse model predicts values of the one or more static parameters. 
     
     
         8 . The method of  claim 4 , wherein the inverse model evaluates an error between the predicted values of one or more measurable input parameters and current measurements of the one or more measurable input parameters, and adjusts the one or more static parameters to minimize the error. 
     
     
         9 . The method of  claim 4 , comprising pre-conditioning execution of the forward model and the inverse model by using an estimated reservoir pressure as a static parameter of the one or more static parameters. 
     
     
         10 . The method of  claim 4 , comprising pre-conditioning execution of the forward model and the inverse model by using an estimated reservoir inflow parameter as a static parameter of the one or more static parameters. 
     
     
         11 . The method of  claim 1 , wherein the one or more additional unmeasurable input parameters comprise fluid density information associated with the one or more fluids. 
     
     
         12 . The method of  claim 11 , wherein the fluid density information is estimated based at least in part on the one or more measurable input parameters comprising a pressure measurement by a fixed downhole pressure gauge. 
     
     
         13 . The method of  claim 1 , wherein at least steps (b)-(e) are performed iteratively via the processing system. 
     
     
         14 . A processing system, comprising:
 one or more processors;   one or more storage media; and   one or more analysis modules comprising computer-executable instructions and associated data, wherein the computer-executable instructions, when executed by the one or more processors, cause the one or more processors to generate a plurality of models stored and updated in the one or more storage media, wherein the plurality of models comprises:
 a forward model configured to predict values of one or more measurable input parameters relating to pumping one or more fluids downhole into a wellbore via coiled tubing; and 
 an inverse model configured to predict one or more unmeasurable input parameters relating to pumping the one or more fluids based on a comparison of the predicted values of the one or more measurable input parameters and current measurements of the one or more measurable input parameters. 
   
     
     
         15 . The processing system of  claim 14 , comprising a network interface configured to communicate with a plurality of sensors. 
     
     
         16 . The processing system of  claim 15 , wherein the plurality of sensors comprises a plurality of downhole sensors and a plurality of surface sensors. 
     
     
         17 . The processing system of  claim 15 , wherein the current measurements of the one or more measurable input parameters are detected by the plurality of sensors. 
     
     
         18 . The processing system of  claim 14 , wherein the plurality of models comprises a mechanical model configured to use the predicted values of the one or more measurable input parameters to predict forces applied to the coiled tubing. 
     
     
         19 . The processing system of  claim 14 , wherein the one or more processors comprises one or more machine learning or artificial intelligence based processors, wherein the processing system is configured to perform modeling or simulation using the one or more machine learning or artificial intelligence based processors, one or more machine learning or AI based algorithms stored in the one or more storage media, or a combinations thereof. 
     
     
         20 . A non-transitory computer-readable medium comprising instructions that, when executed by one or more processors, cause one or more processors to:
 access a real-time pumping schedule for a pump unit configured to pump one or more fluids downhole into a wellbore via coiled tubing, wherein the real-time pumping schedule specifies one or more operational parameters relating to pumping of the one or more fluids;   generate a first model configured to predict values of one or more measurable input parameters relating to pumping of the one or more fluids;   access current measurements of the one or more measurable input parameters detected by one or more sensors;   generate a second model configured to predict one or more unmeasurable input parameters relating to pumping the one or more fluids based on a comparison of the predicted values of the one or more measurable input parameters and the current measurements of the one or more measurable input parameters; and   estimate one or more additional unmeasurable input parameter based at least in part on the one or more measurable input parameters and the one or more unmeasurable input parameters.