Abstract
Measuring the values of weight on bit (WOB) and differential pressure (DiffP) through accurate taring is critical for ensuring downhole tool health and creating accurate parameter roadmaps for drilling optimization. Current industry standards for taring rely on the driller to manually select a particular time when these values are zero, which is often imprecise and/or inaccurate. This paper will detail the journey this drilling contractor made to automate the taring process as part of a broader connection automation initiative, how initial solutions challenged organizational assumptions on downhole behaviors, and how a pattern recognition algorithm allowed for better tare consistency and accuracy over existing field procedures.
An initial process automation procedure was designed and implemented in the rig control system (RCS) to manage the connection process, starting with coming out of slips and ending with tagging bottom. As part of this process, the system included a step to consistently tare when the drill bit is one foot off bottom and descending at a constant rate. During field trials, this method gave encouraging results over previous manual tares. Though the result did show improvement over the traditional manual taring method, discrepancies in the relationship between WOB and DiffP eventually led to an improved method of taring which utilizes a novel pattern recognition algorithm. This algorithm detects when the bit tags bottom and establishes a reference hookload (HKLD) at that point. A pattern recognition algorithm was included into the automation sequence replacing the step to tare one foot from bottom.
The initial process automation routine provided consistency to the taring process which was observed during testing. The improvement in consistency revealed inconsistency in WOB tares which was supported by variance in DiffP when WOB was constant. A pattern recognition method was developed to identify when tagging bottom. This algorithm was applied to historical data providing evidence of its benefit to WOB tares. The algorithm was included in an application and then adapted and applied to DiffP tares. The application was run over a historical dataset to qualify its viability. After proving viability, it was exchanged with the taring step in the initial process automation routine and run on live wells. Taring using the pattern-recognition based application presented better results than the manual and initial automation taring methods. The overall operational impacts of each method will be discussed in further detail.
The results of this project challenge underlying assumptions about how taring should be performed and improves overall understanding of the impact of different automation routines. The pattern recognition method discussed in this paper constitutes a novel application which utilizes new technology to improve existing processes.
