Tool manufacturers have made significant progress improving downhole drilling technologies, but little effort has focused on optimizing the drilling process. The set-it-and-forget-it approach and inherent inefficiencies of the automatic driller are inadequate for keeping bit parameters matched to lithology and wellbore conditions. The industry requires a new methodology to help rig-site personnel make informed drilling parameter decisions based on real-time offset data analysis that increases operating efficiency to reduce drilling costs.
To solve the problem, the service provider launched an artificial neural network (ANN) drilling parameter optimization system (DBOS OnTime) which provides rig-site personnel real-time information to ensure maximum run length from all bits and downhole tools at the highest possible penetration rates (ROP). Benefits of the new system include extended tool life, fewer trips and the ability to manage the bit's dull condition.
The objective is to replace the human factor of applying operating parameters such as weight on bit (WOB) and RPM with the intelligent ANN "learned experience." By using the ANN based software system, operating parameters can be selected based on the documented physical rock characteristics (offset log data) of the formations being penetrated and then fine tuned for the bit's specific cutting structure and wear rate. By following the real-time ANN recommendations, changes can be implemented to increase overall penetration rates (ROP) while maximizing bit life by managing the dull condition.