Semi-Supervised Approach for Early Stuck Sign Detection in Drilling Operations
This work addresses the problem of stuck pipe incidents for drilling operations, offering an incremental improvement over existing methods.
The paper tackles the problem of early stuck pipe detection in drilling operations by proposing a semi-supervised approach using auto-encoders and variational auto-encoders trained on normal drilling data, which showed large reconstruction errors for eight stuck incidents and outperformed previous supervised methods.
A real-time stuck pipe prediction methodology is proposed in this paper. We assume early signs of stuck pipe to be apparent when the drilling data behavior deviates from that from normal drilling operations. The definition of normalcy changes with drill string configuration or geological conditions. Here, a depth-domain data representation is adopted to capture the localized normal behavior. Several models, based on auto-encoder and variational auto-encoders, are trained on regular drilling data extracted from actual drilling data. When the trained model is applied to data sets before stuck incidents, eight incidents showed large reconstruction errors. These results suggest better performance than the previously reported supervised approach. Inter-comparison of various models reveals the robustness of our approach. The model performance depends on the featured parameter suggesting the need for multiple models in actual operation.