Automated and Unmanned Shale Shaker Performance and Borehole Instability Monitoring Using Computer Vision and Artificial Intelligence

Abstract Evaluating the effectiveness of hole cleaning and ensuring wellbore stability is crucial for preventing unwanted events such as kicks or stuck pipes, with consequent minor or major non-productive time (NPT) that, in severe cases, may lead to well abandonment. Beyond the economic implications, these scenarios pose risks of environmental damage and jeopardize the safety of rig personnel. Shale shakers are the first indicator of emerging borehole cleaning and wellbore stability problems and as such, they are a fundamental component of the drilling rig. Detecting cavings and foreign objects on shale shakers is a task typically assigned to humans, who occasionally monitor shaker areas looking at cuttings, and periodically collecting cuttings samples. Monitoring mud beach level and screen damage to preserve drilling mud quality, is also limited to sporadic human observations. These processes lack continuity in monitoring and rely on subjective interpretation of observed samples, often requiring humans to spend significant time in hazardous zones. A novel Computer Vision System for an automated and unmanned shale shaker visual monitoring, coupled with Deep Learning (DL) Artificial Intelligence (AI) models has been implemented. It relies on installing high-speed, high-resolution, explosion-proof cameras continuously acquiring clear and focused pictures of the shale shaker screens at any time during drilling operations. Image data is transmitted up to 500 meters distance and processed through powerful edge computing devices, producing high-frequency objectively interpreted real-time data that can be recorded and plotted along drilling parameters. The system alerts humans to come to the shakers only when necessary. This system has been deployed in three wells across various locations and countries. It aims to replace the traditional human-based monitoring approach by giving a continuous objective detection, and quantification of cuttings, cavings, foreign objects, mud beach level, shaker overflow, and shale shaker screens damage, in real-time. Real-time machine learning based automated detection and interpretation of the shaker screens can substantially improve rig safety by reducing the need for humans to be present in hazardous conditions with fumes and noises when their direct intervention is unnecessary. This system also provides immediate assessment of borehole instability and mud circulation best practices, enabling safer and more effective drilling operations.