July 14, 2021 | 9:00 a.m. - 9:30 a.m. CST (UTC-05:00)

The Rate of Penetration (ROP) is a key criteria for achieving an efficient and productive drilling operation. The ideal ROP depends on multiple geological and operational factors and variables, and this presents a challenging scenario for engineers.

Traditional rule-based optimization techniques are time consuming and may not be able to process the complex interactions between the various drilling parameters. They are also unable to account for the hidden patterns and insights present in historical drilling data. Most importantly, traditional methods do not allow continuous self-learning based on incoming data and thus limits the scalability of the solution.

Halliburton Landmark has developed a machine learning-based approach to simplify this complex process. The proposal is to introduce an AI-based drilling cost/ROP optimization system that can intuitively suggest the optimum operational drilling parameters (weight on bit, rpm, pump flow in, etc.). This system can reduce the overall drilling time and save costs by recommending optimum operational drilling parameters and identify the most effective ROP.