Novel Real-Time Data Analytics Approach for Optimizing Drilling Operations: A Case Study

Abstract

The drilling rig is equipped with a huge number of data sensors that record the operation`s functionalities of different rig systems, personnel, and equipment. Integrating such data, transmitting through data transformation protocols, and accomplishing real-time data analytics will greatly contribute to enhancing the drilling operation performance, mitigating the drilling hazards, minimizing invisible lost time (ILT), and reducing the operation cost. Real-time data analytics show the key performance indicators (KPIs) for every operation on the rig in terms of drilling, tripping, connection, etc., to reveal the data insights for the best decision-making using the advanced visualization dashboards and reporting system. The current research shows the high capabilities of data analytics in real-time through a novel integrated approach for multi-source data toward enhancing the operation performance and reducing the drilling cost with a real field case study.

This paper presents an integrated systematic data analytics workflow for real-time rig sensors and daily drilling reports to efficiently monitor and enhance operations performance. The novel developed approach provides an accurate measurement of operations indicators and identification of potential improvements for the drilling operation. The system aggregates and processes the data transmitted from the drilling rigs and integrates it with daily drilling reporting. Operation performance is displayed through benchmark analyses from all rigs, by operation type, and equipment, giving a statistical indication of the technical limit to reduce ILT. The paper shows a real field case study to present drilling operation efficiency enhancement through real-time data analytics.

25% of the drilling operation is considered ILT, and this might be reduced through advanced data analytics for the drilling data. The developed approach provides impartial and detailed KPIs on operation performance to determine and eliminate ILT. Through a case study, the results showed an enhancement of up to 10% in time-saving and cost reduction. This amount of time is saved by adjusting these parameters in real-time based on the insights provided by the analytics system, resulting in optimized efficiency and cost reduction. The developed approach is currently upgraded with developed machine-learning models for prediction and classification purposes through advanced computational algorithms to predict the rate of penetration and drilling hazards and auto-detect the drilled formation type/class from collected drilling data.

Overall, the novel approach presented within the study shows that real-time data analytics can significantly improve drilling efficiency by identifying patterns and trends in data and providing actionable insights that can be used to optimize drilling operations. This has the potential to reduce drilling costs, improve safety, and increase the overall efficiency of drilling operations.