Geomechanics, ECD Management and RSS to Manage Drilling Challenges in a Mature Field

Abstract

The Serang Field, offshore East Kalimantan, Indonesia was discovered in 1973. Production started in 1993. Although it is a mature field with 120 wells, drilling still faces challenges in the form of severe lost circulation and stuck pipe events. Side tracks often need to be drilled and drilling budget overruns can be significant. The 2006 drilling campaign of 5 wells saw the loss of several BHAs and needed 4 sidetracks, due to stuck pipe events. In order to improve the drilling operation and to uncover root causes of the losses and pack-offs, a detailed geomechanical evaluation was conducted. The study began with a comprehensive data audit and drilling event review. All the captured information and log data was then used to create a Mechanical Earth Model (MEM) for wellbore stability planning of future wells. Key findings of the study were that lost circulation occurred in high permeability zones in shallow carbonates (8-1/2" intermediate hole section) and were not caused by drilling induced fractures. A contingency plan was developed to drill to section TD with sea water, should losses occur. Breakouts, aggravated by low mud weights, lost circulation events, high deviation and slim hole contributed to poor hole cleaning, which caused the packoff incidents in the 6 1/8" sections. Safe and stable mud weight windows were established to mitigate hole collapse and stuck pipe. Since losses can occur even at low mud weights but do not usually have severe consequences, the team decided it was more important to focus on avoiding breakouts and improve hole cleaning with higher mud weights, improved drilling fluids with stress cage system to drill through depleted reservoirs, controlled drilling, ECD management to prevent formation breakdown and the use of Rotary Steerables to improve hole cleaning. The recommendations of the study were incorporated during a 3 well drilling campaign in 2009. All 3 wells were drilled and completed within budget and without stuck pipe incidents.

Machine Learning Models for Equivalent Circulating Density Prediction from Drilling Data

“…11,12 Ignoring these parameters will affect the ECD prediction, lead to inaccurate evaluation of ECD, and cause well control problems during the drilling operations. 13,14 ■ PREDICTING ECD BY EMPLOYING ML TECHNIQUES ECD prediction from the drilling data is considered a novel approach in the petroleum industry due to the limitations of the ECD downhole measurements. AI is a technique that utilizes high computing capabilities for processing advanced algorithms to solve technical/problematic issues by simulating the human brain's thinking manner.…”

“…The developed mathematical correlations are limited to some applications, and they ignore a lot of other input parameters that have an impact on the ECD values. Such ignored parameters are well geometry, fluid rheological properties, rotation of the drill string, and downhole pressure and temperature conditions, which affect the mud density, cuttings dispersion, hole cleaning, and swab and surge of drill pipe movements in the hole. , Ignoring these parameters will affect the ECD prediction, lead to inaccurate evaluation of ECD, and cause well control problems during the drilling operations. , …”

Intelligent Prediction of The Equivalent Circulating Density From Surface Data Sensors During Drilling By Employing Machine Learning Techniques

“…Such ignored parameters as well geometry, fluid rheological properties, the rotation of the drill string, downhole pressure and temperature conditions that affect the mud density, cuttings dispersion, hole cleaning, and swab and surge of drillpipe movements in the hole 12,13 . Ignoring these parameters will affect the ECD prediction and lead to the inaccurate evaluation of ECD and causes well control problems during the drilling operations 14,15 .…”

Wellbore breakout prediction in transversely isotropic rocks using true-triaxial failure criteria

“…The role of geomechanics in minimising excessive drilling costs has been acknowledged by many researchers. Several authors [1][2][3][4][5][6][7] reported the benefit of having a pre-drilling geomechanical model. Their respective drilling challenges have been addressed by means of, but not limited to, the construction of a robust stress profile, the estimation of the rock elastic and strength properties, drilling trajectory evaluation, drilling fluid properties optimization, and casing seat design.…”

“…They reported that the non-productive time (NPT) could be reduced to as low as 2% by implementing pre-drill geomechanical modelling and real-time drilling geomechanics surveillance. Caicedo et al [2] also reported that the stuck pipe incidents could be eliminated after introducing a geomechanical approach into their drilling campaign. Their statistic reflects evidence that NPT was primarily associated with series of mud loss and pack-offs; however, the root cause of these incidents was initially unidentified.…”