Drilling & Fracturing Optimization

Drilling problems such as stick slip vibration/hole cleaning, pipe failures, loss of circulation, BHA whirl, stuck pipe incidents, excessive torque and drag, low ROP, bit wear, formation damage and borehole instability, and the drilling of highly tortuous wells have only been tackled using physics-based models. 

Hydraulic fracturing posses an additional suite of problems. Operators are excpected to rely on their experience, gut feeling and current well parameters. We utilize data-driven approaches to provide meter-by-meter fracturing gun speed recommendations. These take into account the speeds in well sections from other wells woith similar shape, inclination profile and geology. Cable readings and history is taken into account to minimize wear & tear and chance of breakage/ incident.

Currently there is a tremendous gap between statistical based models and empirical, mathematical, and physical-based models. Data mining techniques have made prominent contributions across a broad spectrum of industries.

Here at MLTune we have accumulated an extensive experience in Signal anomaly detection of the temporal data coming from the drilling operations. Utilizing the drilling parameters and real data we have developed an ML based solution for formation position and drilling conditions tracking.