Self-Learning Probabilistic Detection and Alerting of Drillstring Washout and Pump Failure Incidents During Drilling Operations
Ambrus A, Ashok P, Ramos D, Chintapalli A, Susich A, Thetford T, Nelson B, Shahri M McNab J and Behounek M: “Self-Learning Probabilistic Detection and Alerting of Drillstring Washout and Pump Failure Incidents During Drilling Operations,” paper IADC/SPE 189700, presented at the IADC/SPE Drilling Conference and Exhibition, Fort Worth, Texas, March 6–8, 2018.
Recently, Intellicess applied unique beliefs-based early detection and alerting system to drillstring washout and pump failure detection during drilling. The methodology was used to focus primarily on the time signatures of real-time and modeled pump pressure in relation to flow rate trends. Together these parameters described the status of the equipment, which was then assessed through real-time alerts. Case histories presented demonstrate that through continuous model improvements and validation, the Intellicess system was able to detect the warning signs of washout and pump failure hours before the problem was detected at the rig site. As a consequence, significant value was added through early detection of mechanical failures that allowed the driller to significantly reduce non productive time caused by pump downtime, tripping, and fishing.