ML / Done

Shale Shaker Cutting Estimations (Desktop)

Role | Internship Machine Learning Engineer Timeline | 6 months

Overview

Desktop-based (v1) computer vision system to monitor and analyze rock cuttings from shale shakers in real-time using CCTV footage, integrated with the WITSML realtime drilling data standard. Built with classical OpenCV image processing, without deep learning. The system was designed to improve the efficiency and accuracy of drilling process monitoring by providing real-time data on rock coverage and composition, thereby supporting operational decision-making in the oil and gas industry.

Challenge

The primary challenges included processing video streams in real-time with minimal latency, accurately detecting and analyzing rock cuttings amidst varying lighting conditions and potential noise, and keeping the system reliable and scalable enough to plug into monitoring systems like the Early Monitoring System (EMS).

Result

The deployed system provided real-time monitoring of shale shaker cuttings, enabling more informed decision-making during drilling operations. It achieved high accuracy in detecting rock coverage and composition, with visualizations helping to identify trends in rock composition over time. The system was integrated with the Early Monitoring System, enhancing overall operational efficiency and reducing manual monitoring efforts.