Machine Learning Application in Enhancing Drilling Performance

Abstract

Drilling Oil and Gas wells is an expensive operation, where the cost for drilling a single shallow offshore HP-UHT well may exceed 30 million USD easily. Due to the huge cost involved, companies are eager to accomplish the drilling operations in a minimal time frame, by increasing the drilling rate or rate of penetration (ROP) and reducing the downhole tool failures. The Mechanical Specific Energy (MSE) concept addresses these two drilling performance measures in totality as it provides maximum ROP which can be achieved with the existing drilling system (i.e., Drill Bits, Drilling Tubular, Well Profile, and Mud weight) without causing downhole tool failures. ROP is a function of Weight on Bit, Rotation per Minute, and Flow rate for an existing drilling system, optimization of these parameters results in increased ROP, whereas unharmonious values lead to shock and vibration in drilling assembly. Machine Learning algorithms facilitate this optimization of drilling parameters for enhancing drilling performance, by the development of an accurate ROP prediction and optimization model. The ROP prediction model was developed using Artificial Neural Network and Random Forest, and the optimization model was developed using evolutionary optimization algorithms like particle swarm optimization and genetic algorithms. The result of the optimization model depends upon the accuracy of the ROP prediction model and the upper and lower limits of drilling parameters defined in the optimization model. Machine learning applications in improving the Drilling Performance can be easily quantified in terms of saving days, where one day of operational cost for the company is approximately 0.2 million USD per Offshore – HP-UHT well.

Topics & Concepts