AI-Automated Codification-QC Model for Daily Drilling Reports

In the oil and gas industry, Daily Drilling Reports (DDRs) are vital to the well life cycle. Drilling supervisors meticulously record every detail of daily operations, ensuring accurate data is readily accessible for future use. This information is crucial for optimizing operations and future decision-making. However, manually preparing and coding these reports is both time-consuming and costly, introducing the risk of errors that can compromise data quality. Having accurate data and correct classification of drilling activities are key to making decisions that boost drilling efficiency and cut costs. The precision of DDRs affects how well drilling operations can be analyzed and optimized. But, manual codification by the rig crew often leads to errors, with mistakes in 10% to 20% of entries. These errors stem from the difficulty of categorizing over 400 unique drilling activities, leading to wrong classifications that can disrupt operations and cause expensive errors. This is where Quality Control (QC) comes in, playing a crucial role in making sure DDRs are accurate. However, QC faces similar challenges, requiring highly experienced engineers to spot and correct errors from the initial coding. These QC engineers need a deep understanding of drilling operations and must be able to pick up on subtle errors in many categories. The complexity and high skill requirements make the QC process as lengthy and prone to errors as the initial coding, highlighting the need for more reliable and efficient methods.